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

    Neuronpedia

    INDEX
    Explanations

    words related to pricing or setting values

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with technical specifications or attributes related to products and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sack
    -0.71
    eeks
    -0.71
    hur
    -0.69
    女
    -0.67
    rance
    -0.67
    Found
    -0.67
    acio
    -0.65
    umbn
    -0.63
    roma
    -0.63
    vous
    -0.63
    POSITIVE LOGITS
     differently
    1.08
     accordingly
    1.01
     correctly
    0.90
     by
    0.89
     incorrectly
    0.88
    ependent
    0.87
     appropriately
    0.85
     externally
    0.83
     properly
    0.82
    ulously
    0.80
    Act Density 0.210%

    No Known Activations