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

    Neuronpedia

    INDEX
    Explanations

    words related to various methods or activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     constitu
    -0.73
    ĺħ
    -0.69
     Hurricanes
    -0.68
     Kag
    -0.63
     diplom
    -0.61
     chast
    -0.60
     prec
    -0.60
     deliberations
    -0.59
     Bastard
    -0.59
     Dh
    -0.58
    POSITIVE LOGITS
    ings
    1.66
    ables
    1.58
    ers
    1.52
    able
    1.48
    ability
    1.38
    aways
    1.38
    away
    1.32
    downs
    1.27
    ership
    1.25
    outs
    1.25
    Act Density 0.204%

    No Known Activations