Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    quantifiers and references to quantities or relationships among items or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "of" followed by a pronoun or relative pronoun

    np_acts-logits-general · gemini-2.0-flash

    of whom / them / which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     occhiali
    -0.52
     serangga
    -0.49
     zoveel
    -0.47
    AndEndTag
    -0.43
    IGraphics
    -0.42
     cohomology
    -0.40
     periódicos
    -0.40
    ത്തി
    -0.38
    ;}
    -0.38
    exitRule
    -0.38
    POSITIVE LOGITS
     שוליים
    0.88
     which
    0.82
     TextInputType
    0.75
    IsContent
    0.73
     being
    0.72
     IDisposable
    0.69
    Примітки
    0.69
     containing
    0.65
     antaranya
    0.65
    verwijspagina
    0.65
    Act Density 0.172%

    No Known Activations