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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "is"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.94
     cdti
    -0.94
     itſelf
    -0.91
     NgModule
    -0.87
    LookAnd
    -0.86
     ligiloj
    -0.85
     reft
    -0.84
     Akismet
    -0.83
    InjectAttribute
    -0.83
    الدراسه
    -0.82
    POSITIVE LOGITS
     real
    0.71
     the
    0.68
     THIS
    0.66
     a
    0.61
    __(/*!
    0.60
     really
    0.59
    oss
    0.58
    あく
    0.58
     this
    0.57
     This
    0.56
    Act Density 0.118%

    No Known Activations