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

    Neuronpedia

    INDEX
    Explanations

    negative constructions in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eer
    -0.17
     BOTH
    -0.16
     both
    -0.15
    sort
    -0.15
     både
    -0.15
     Both
    -0.15
    ses
    -0.15
    isposable
    -0.14
    .WinForms
    -0.14
     Already
    -0.14
    POSITIVE LOGITS
     does
    0.30
     nor
    0.26
     yet
    0.26
     any
    0.26
     did
    0.26
    theless
    0.25
     anybody
    0.24
     anyone
    0.24
     necessarily
    0.24
     anymore
    0.23
    Act Density 0.022%

    No Known Activations