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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating degree or level for various situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of comparisons or contrasts that highlight surprising or noteworthy characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dayName
    -0.76
    uum
    -0.74
    renheit
    -0.72
    icide
    -0.71
    nery
    -0.67
    onomic
    -0.66
     whoever
    -0.62
    Jump
    -0.60
     Beetle
    -0.60
    uilding
    -0.59
    POSITIVE LOGITS
     noteworthy
    0.85
     notable
    0.83
    details
    0.81
     irony
    0.80
    noticed
    0.73
     downside
    0.73
     bombshell
    0.72
     importantly
    0.71
     facet
    0.71
    paralle
    0.71
    Act Density 0.405%

    No Known Activations