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

    Neuronpedia

    INDEX
    Explanations

    words related to support or opposition

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to support, approval, and backing for various initiatives or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tnc
    -0.86
    ondo
    -0.69
    dule
    -0.67
    ²¾
    -0.66
    eria
    -0.64
     Grimoire
    -0.63
     lookout
    -0.61
    corn
    -0.60
    insert
    -0.58
    =#
    -0.57
    POSITIVE LOGITS
     from
    0.98
     among
    0.91
     amongst
    0.89
    from
    0.80
     FROM
    0.80
     elsewhere
    0.79
     internationally
    0.79
     locally
    0.79
     outside
    0.75
     nationally
    0.75
    Act Density 0.187%

    No Known Activations