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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or making changes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to taking action or making changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ère
    -0.69
     Sloan
    -0.62
     thanking
    -0.60
    eret
    -0.59
     telling
    -0.57
     referring
    -0.56
     specializing
    -0.56
    orsi
    -0.55
     Ãī
    -0.55
     extending
    -0.54
    POSITIVE LOGITS
     oneself
    0.97
     Yourself
    0.72
    olitical
    0.70
    endas
    0.68
    iped
    0.61
     wrong
    0.59
     idols
    0.58
    rows
    0.57
    pless
    0.57
    mercial
    0.56
    Act Density 0.948%

    No Known Activations