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

    Neuronpedia

    INDEX
    Explanations

    references to relationships and manipulative dynamics between individuals

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

    Following prepositions and possessive pronouns

    np_acts-logits-general · gemini-2.0-flash

    his taking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -1.13
     betweenstory
    -0.95
     pinulongan
    -0.92
    RectangleBorder
    -0.89
    DockStyle
    -0.87
    ".
    -0.87
    ")));
    -0.86
     متعلقه
    -0.84
    Tembelea
    -0.83
     myſelf
    -0.83
    POSITIVE LOGITS
     his
    0.55
     us
    0.52
     contigo
    0.49
     conmigo
    0.46
    (
    0.45
    ​
    0.44
    -
    0.44
     +
    0.43
    нок
    0.41
    .
    0.41
    Act Density 0.890%

    No Known Activations