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

    Neuronpedia

    INDEX
    Explanations

    comparisons in terms of relationships

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to relative comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spr
    -1.10
    mberg
    -0.81
    ERG
    -0.81
    printed
    -0.81
    vous
    -0.79
    creen
    -0.76
    iere
    -0.76
    erb
    -0.75
    storm
    -0.75
    berry
    -0.74
    POSITIVE LOGITS
     relative
    0.95
     exha
    0.84
     pressures
    0.83
     humidity
    0.82
     abund
    0.81
     aggro
    0.79
     earthqu
    0.78
     simultane
    0.77
     uncle
    0.77
     nephew
    0.77
    Act Density 0.007%

    No Known Activations