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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or acronyms related to organizations or entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Miami

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holders
    -0.78
    ional
    -0.78
    ding
    -0.77
    \\\\\\\\
    -0.77
    sworth
    -0.76
    size
    -0.76
    holder
    -0.75
    mans
    -0.73
    metic
    -0.72
    grounds
    -0.72
    POSITIVE LOGITS
    AMI
    1.19
    PS
    1.04
    HAEL
    0.96
    KE
    0.89
    XT
    0.84
    uppet
    0.80
    ovember
    0.79
    LE
    0.79
    eredith
    0.77
    OSH
    0.76
    Act Density 0.014%

    No Known Activations