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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical descriptions and characteristics

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and descriptors that convey emotional or subjective evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¬¼
    -0.84
    swick
    -0.78
    afety
    -0.77
    OND
    -0.67
    uay
    -0.67
    URA
    -0.66
    OME
    -0.65
    thora
    -0.62
    §
    -0.62
    UF
    -0.61
    POSITIVE LOGITS
     albeit
    1.04
     but
    0.97
     though
    0.88
     although
    0.88
     however
    0.85
     huh
    0.83
     whereas
    0.81
     except
    0.79
    yet
    0.74
     eg
    0.73
    Act Density 0.448%

    No Known Activations