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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the ability to do something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    furt
    -0.76
     Irving
    -0.70
     revision
    -0.69
     rejection
    -0.66
     Strikes
    -0.63
     Cance
    -0.62
     UR
    -0.61
     Likes
    -0.61
     Uri
    -0.58
     IB
    -0.57
    POSITIVE LOGITS
    't
    1.45
    berra
    1.19
    adian
    1.12
     afford
    1.01
    NOT
    0.96
     muster
    0.89
     feas
    0.87
    nery
    0.85
    ieve
    0.85
     be
    0.80
    Act Density 0.170%

    No Known Activations