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

    Neuronpedia

    INDEX
    Explanations

    adverbs describing the intensity or quality of attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    fairly followed by adjectives/adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Erreferentziak
    -0.40
     때문
    -0.37
     navíc
    -0.36
    excess
    -0.35
     millones
    -0.34
    rzez
    -0.33
     transparencia
    -0.33
    endalikan
    -0.32
    Customer
    -0.32
     autorizado
    -0.32
    POSITIVE LOGITS
     fairly
    1.14
     Fairly
    1.02
     довольно
    1.00
     abbastanza
    1.00
     ganska
    0.98
     assez
    0.96
     khá
    0.95
     relatively
    0.94
     Relatively
    0.94
     dość
    0.93
    Act Density 0.066%

    No Known Activations