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

    Neuronpedia

    INDEX
    Explanations

    verbs related to desires or intentions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     faint
    -0.63
    mone
    -0.61
     suicides
    -0.58
     wheelchair
    -0.58
     mayors
    -0.58
     TTL
    -0.58
     attrition
    -0.56
     haz
    -0.56
    hero
    -0.55
    rid
    -0.55
    POSITIVE LOGITS
     beforehand
    0.80
    ãĤ´
    0.77
     happening
    0.74
    _.
    0.70
    ETS
    0.69
    FontSize
    0.68
    ?:
    0.66
     besides
    0.65
     regarding
    0.65
    advertisement
    0.64
    Act Density 0.169%

    No Known Activations