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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or plans

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     wont
    -0.73
    pmwiki
    -0.70
    ItemTracker
    -0.64
    cember
    -0.63
    æ©Ł
    -0.61
     marked
    -0.56
    Avg
    -0.56
     seldom
    -0.56
     indicating
    -0.56
     doubtless
    -0.56
    POSITIVE LOGITS
    uate
    1.17
     oneself
    1.08
    enance
    0.92
     them
    0.87
    igate
    0.87
    urate
    0.84
    dress
    0.82
     anything
    0.82
    ulate
    0.81
    ezvous
    0.81
    Act Density 3.625%

    No Known Activations