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

    Neuronpedia

    INDEX
    Explanations

    phrases related to obstacles or challenges

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe paths or methods of accomplishing tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uster
    -0.77
    usters
    -0.76
    encer
    -0.75
    incinn
    -0.66
    anmar
    -0.65
    icio
    -0.65
     Gru
    -0.64
    grave
    -0.63
    akov
    -0.63
    encers
    -0.63
    POSITIVE LOGITS
    fare
    1.06
    finding
    0.92
    point
    0.89
    ward
    0.87
    forward
    0.74
    aterasu
    0.73
     WAY
    0.73
    points
    0.72
     Judaism
    0.71
    drive
    0.71
    Act Density 0.070%

    No Known Activations