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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating openness or receptiveness to various scenarios or ideas

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a willingness to accept or consider new ideas or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raints
    -0.60
    IRE
    -0.60
     Zot
    -0.58
    olation
    -0.58
     superflu
    -0.58
    UID
    -0.57
    uke
    -0.57
    urations
    -0.56
    sis
    -0.55
     undes
    -0.54
    POSITIVE LOGITS
     enough
    0.95
    wired
    0.86
    minded
    0.86
     minded
    0.84
     spirited
    0.79
    iltr
    0.78
    ãĥ¼ãĤ¯
    0.76
     unto
    0.76
    imately
    0.75
    handedly
    0.75
    Act Density 0.117%

    No Known Activations