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

    Neuronpedia

    INDEX
    Explanations

    adjectives expressing degree or intensity

    oai_token-act-pair · gpt-3.5-turbo

    adjectives describing various degrees of quality or magnitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewed
    -0.83
    uther
    -0.76
    ecause
    -0.75
     Helpful
    -0.71
    rarily
    -0.71
    Gi
    -0.69
    KER
    -0.69
    forge
    -0.68
     Alternatively
    -0.67
    Newsletter
    -0.66
    POSITIVE LOGITS
     counterparts
    1.01
     foray
    1.01
     fortunes
    0.97
     exploits
    0.96
    ness
    0.96
     creations
    0.94
     nature
    0.94
     cousin
    0.94
     arsenal
    0.93
     predecessors
    0.93
    Act Density 0.232%

    No Known Activations