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

    Neuronpedia

    INDEX
    Explanations

    phrases related to options or alternatives

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and related phrases that connect different ideas or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ledged
    -0.71
    Ö¼
    -0.69
    ©¶æ¥µ
    -0.67
    lass
    -0.65
    etheless
    -0.64
    gyn
    -0.63
    gian
    -0.63
    atan
    -0.62
    ishi
    -0.62
    onet
    -0.62
    POSITIVE LOGITS
     purposes
    1.19
     sake
    1.03
     amusement
    0.97
     souven
    0.83
     convenience
    0.82
     fodder
    0.79
     enthusiasts
    0.79
     occasional
    0.78
     enjoyment
    0.78
     entertainment
    0.77
    Act Density 0.363%

    No Known Activations