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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific details or events

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to discomfort and contentious social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sbm
    -0.67
    /
    -0.65
    umbn
    -0.64
    20439
    -0.62
    arthed
    -0.61
     Seym
    -0.60
    epend
    -0.60
    ãĢij
    -0.58
     ];
    -0.58
    escription
    -0.57
    POSITIVE LOGITS
    ?!
    1.79
    !?
    1.65
     huh
    1.63
    ?
    1.62
    ???
    1.50
    ??
    1.48
    ...?
    1.47
    .?
    1.42
    ?!"
    1.37
    ????
    1.36
    Act Density 0.903%

    No Known Activations