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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or addressing issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to addressing significant social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urt
    -0.79
    akin
    -0.72
    abet
    -0.64
    handler
    -0.64
    eled
    -0.63
    parents
    -0.59
    ety
    -0.58
    Render
    -0.58
    appointed
    -0.57
    iew
    -0.57
    POSITIVE LOGITS
     tackle
    0.79
    ãĥ¯ãĥ³
    0.76
    ahime
    0.75
    tackle
    0.74
    rolet
    0.73
     tackling
    0.72
    é¾
    0.69
    cliffe
    0.69
    cture
    0.69
     tackles
    0.66
    Act Density 0.023%

    No Known Activations