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

    Neuronpedia

    INDEX
    Explanations

    terms related to infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    references to infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CVE
    -0.72
    Cam
    -0.64
    DOS
    -0.63
     clay
    -0.63
    bed
    -0.61
     accompanying
    -0.60
    Shock
    -0.60
    Dutch
    -0.59
    Williams
    -0.59
     residency
    -0.58
    POSITIVE LOGITS
    rast
    1.38
    inators
    0.92
    inating
    0.89
    ination
    0.88
    minist
    0.84
    aic
    0.83
    algia
    0.78
    ruct
    0.77
    ics
    0.77
    byss
    0.76
    Act Density 0.008%

    No Known Activations