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

    Neuronpedia

    INDEX
    Explanations

    verbs related to taking or stealing

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions of taking or stealing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ratulations
    -0.84
    anim
    -0.81
    KK
    -0.79
    wcs
    -0.79
    iter
    -0.78
    ascript
    -0.77
    seek
    -0.75
    motion
    -0.74
    airs
    -0.74
    ICA
    -0.73
    POSITIVE LOGITS
     afar
    1.18
     whence
    1.00
     somewhere
    0.93
     thence
    0.92
     abroad
    0.89
     scratch
    0.87
     anywhere
    0.81
     elsewhere
    0.78
     everywhere
    0.78
     wherever
    0.78
    Act Density 0.118%

    No Known Activations