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

    Neuronpedia

    INDEX
    Explanations

    words related to negation or lack of action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BeginContext
    -0.70
    PhysRevLett
    -0.66
     veci
    -0.57
    lapia
    -0.55
     Pingback
    -0.52
    </i>
    -0.52
    Special
    -0.51
    XmlType
    -0.50
     وتسجيلات
    -0.49
    PhysRevD
    -0.49
    POSITIVE LOGITS
     uncut
    0.99
     unbroken
    0.91
     unex
    0.90
     untouched
    0.89
     undis
    0.88
     Unused
    0.88
     unmodified
    0.87
     unanswered
    0.86
     unused
    0.84
     undisturbed
    0.83
    Act Density 0.230%

    No Known Activations