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

    Neuronpedia

    INDEX
    Explanations

    words related to reduction or decrease

    oai_token-act-pair · gpt-3.5-turbo

    words related to reduction or decrease

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REL
    -0.80
    ullivan
    -0.77
    spot
    -0.70
    raid
    -0.67
     Aval
    -0.65
    rera
    -0.65
    sol
    -0.65
    ILLE
    -0.65
    find
    -0.63
     Advice
    -0.62
    POSITIVE LOGITS
    inished
    0.88
    utive
    0.86
     proport
    0.84
    ments
    0.77
    mentation
    0.74
    ishment
    0.72
    itized
    0.71
    initions
    0.69
    iasis
    0.69
    ighed
    0.68
    Act Density 0.033%

    No Known Activations