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

    Neuronpedia

    INDEX
    Explanations

    words related to plans or strategies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to strategies or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mare
    -0.79
    nick
    -0.77
    edin
    -0.72
    clair
    -0.71
    ofi
    -0.70
    RIP
    -0.70
    cles
    -0.69
    \<
    -0.67
    hai
    -0.66
    ATH
    -0.66
    POSITIVE LOGITS
    gery
    1.23
    bidden
    1.12
    geries
    1.06
    gotten
    0.91
     determining
    0.91
     purposes
    0.87
    aging
    0.86
     constructing
    0.85
     resolving
    0.83
     combating
    0.83
    Act Density 0.184%

    No Known Activations