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

    Neuronpedia

    INDEX
    Explanations

    phrases related to involvement in various activities or projects

    oai_token-act-pair · gpt-3.5-turbo

    references to actions or activities that require participation or entail certain requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TI
    -0.72
    hat
    -0.66
    heit
    -0.63
    onew
    -0.62
     desks
    -0.60
    toggle
    -0.60
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.59
    soon
    -0.59
    itudinal
    -0.58
    century
    -0.57
    POSITIVE LOGITS
    ioned
    0.72
     involving
    0.69
     removing
    0.68
    cius
    0.68
    poke
    0.67
    olved
    0.66
     brute
    0.66
    itaire
    0.65
     importing
    0.64
    rontal
    0.62
    Act Density 0.044%

    No Known Activations