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

    Neuronpedia

    INDEX
    Explanations

    words related to changes or alterations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to alterations or adjustments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Water
    -0.74
    ä
    -0.73
    çĦ
    -0.73
    True
    -0.71
    Ranked
    -0.71
    Å
    -0.69
    ç«
    -0.69
    JC
    -0.68
    é£
    -0.67
    tre
    -0.65
    POSITIVE LOGITS
    xual
    1.06
     modification
    0.96
    atile
    0.92
     modifications
    0.92
     carbohyd
    0.92
     mathemat
    0.89
    hap
    0.89
     nomine
    0.88
     ende
    0.86
    atility
    0.85
    Act Density 0.010%

    No Known Activations