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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases signaling actions or intentions

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "to" as part of various phrases indicating intention or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emetery
    -0.82
     Chronicle
    -0.71
    sle
    -0.70
     Occupations
    -0.70
     Malone
    -0.69
     Typ
    -0.69
     Canary
    -0.67
    Alias
    -0.66
     Louie
    -0.66
     Mysteries
    -0.66
    POSITIVE LOGITS
     intervene
    1.35
     negotiate
    1.31
     retaliate
    1.31
     cooperate
    1.30
     extrad
    1.30
     annex
    1.28
     invade
    1.23
     intensify
    1.22
     impose
    1.19
     strengthen
    1.19
    Act Density 0.239%

    No Known Activations