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

    Neuronpedia

    INDEX
    Explanations

    verbs related to authority or commands

    oai_token-act-pair · gpt-3.5-turbo

    instances of desire or intent related to actions or responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     compat
    -0.60
    affected
    -0.60
    oké
    -0.57
     brun
    -0.57
    caps
    -0.55
    onge
    -0.55
    colo
    -0.54
    owan
    -0.53
    hello
    -0.51
     hairst
    -0.51
    POSITIVE LOGITS
    ĸļ
    0.78
     antitrust
    0.68
     itself
    0.68
    ãĥ³ãĤ¸
    0.67
     unilaterally
    0.66
     sanction
    0.65
     tacit
    0.63
     capit
    0.63
     acquies
    0.62
     appoint
    0.62
    Act Density 0.809%

    No Known Activations