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

    Neuronpedia

    INDEX
    Explanations

    phrases related to matters of concern or interest

    oai_token-act-pair · gpt-3.5-turbo

    references to issues or topics of concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocene
    -0.83
    ammy
    -0.82
    orne
    -0.80
    orah
    -0.77
    obs
    -0.76
    arak
    -0.75
    owler
    -0.73
    ierre
    -0.71
    aido
    -0.70
    tein
    -0.70
    POSITIVE LOGITS
     concerning
    1.10
     regarding
    0.78
    ments
    0.77
    atform
    0.73
     respecting
    0.70
     Regarding
    0.68
     newsp
    0.66
     unanswered
    0.65
     Ambro
    0.65
    EngineDebug
    0.64
    Act Density 0.006%

    No Known Activations