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

    Neuronpedia

    INDEX
    Explanations

    quotes or statements that are considered inappropriate or unwarranted

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "call."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Jump
    -0.75
    orters
    -0.73
    orter
    -0.65
    Flo
    -0.64
    ositories
    -0.63
    duc
    -0.63
    lr
    -0.63
    zin
    -0.61
    dfx
    -0.61
    iosyncr
    -0.61
    POSITIVE LOGITS
     999
    0.83
    axy
    0.77
    adesh
    0.71
    ares
    0.69
    arded
    0.68
    arding
    0.66
     Geological
    0.66
    arie
    0.65
    ategory
    0.64
    alled
    0.64
    Act Density 0.012%

    No Known Activations