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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing emotional states

    oai_token-act-pair · gpt-3.5-turbo

    emotional states and adjectives describing feelings or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usalem
    -0.60
     Brief
    -0.56
     unim
    -0.56
    aleb
    -0.55
    uly
    -0.55
    arser
    -0.55
     gradual
    -0.54
     brief
    -0.54
     clipboard
    -0.54
    few
    -0.54
    POSITIVE LOGITS
     indeed
    0.80
     insofar
    0.75
    Ùİ
    0.70
     (>
    0.70
    ––
    0.69
    isable
    0.68
     âĶľ
    0.67
    Ùĩ
    0.66
     attRot
    0.65
    icative
    0.65
    Act Density 0.255%

    No Known Activations