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

    Neuronpedia

    INDEX
    Explanations

    contractions and informal language

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or suggestions for action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "},
    -0.73
    POL
    -0.71
    æ©Ł
    -0.65
    Js
    -0.64
    VERTISEMENT
    -0.62
    Changes
    -0.60
    DragonMagazine
    -0.60
    ãĥķ
    -0.60
     Rosa
    -0.58
    WOR
    -0.56
    POSITIVE LOGITS
     unsure
    0.96
     interested
    0.80
     adventurous
    0.76
     inclined
    0.76
     lucky
    0.74
     wondering
    0.69
     subscrib
    0.68
     fortunate
    0.66
    oubted
    0.66
     yourself
    0.66
    Act Density 0.164%

    No Known Activations