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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases related to actions or commands

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to processes or operations that involve utilization or benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sie
    -0.64
    Stage
    -0.62
    ricks
    -0.61
    anz
    -0.60
    pard
    -0.60
    stage
    -0.60
    rea
    -0.59
     Lauder
    -0.58
     Gentleman
    -0.57
     reluct
    -0.57
    POSITIVE LOGITS
     neither
    0.71
    é¾įå¥ij士
    0.65
     nothing
    0.63
    otta
    0.60
     both
    0.60
    ulic
    0.59
    auna
    0.59
    itates
    0.59
    ļéĨĴ
    0.58
    araoh
    0.57
    Act Density 0.366%

    No Known Activations