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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a breakout or standout performance or achievement

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant performances or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ittee
    -0.83
    poral
    -0.81
    cale
    -0.79
    zanne
    -0.78
    anamo
    -0.78
    esthetic
    -0.77
    anto
    -0.77
    teness
    -0.75
    rox
    -0.73
    alach
    -0.73
    POSITIVE LOGITS
     breakout
    1.07
    draft
    1.03
    PsyNetMessage
    0.83
    SpaceEngineers
    0.82
     hatch
    0.69
     Marshall
    0.68
    OWS
    0.67
    knit
    0.66
    WER
    0.65
     Synd
    0.64
    Act Density 0.011%

    No Known Activations