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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a failure to meet expectations or standards

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating inadequacy or failure to meet expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antine
    -0.72
    uo
    -0.69
    Il
    -0.68
    RAW
    -0.67
    allic
    -0.66
    ILLE
    -0.65
    uala
    -0.64
     Disp
    -0.63
    GEN
    -0.63
    ITAL
    -0.63
    POSITIVE LOGITS
    sighted
    1.05
    falls
    1.01
    ening
    0.86
    casts
    0.81
    eners
    0.77
    leaf
    0.76
    lived
    0.74
     enough
    0.70
    ened
    0.70
    skirts
    0.70
    Act Density 0.018%

    No Known Activations