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

    Neuronpedia

    INDEX
    Explanations

    words related to a specific person, possibly named Jennifer

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "aff"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CHR
    -0.96
    OPER
    -0.74
    senal
    -0.69
     Penal
    -0.62
     Santana
    -0.61
     Patriarch
    -0.61
    OPLE
    -0.61
     Peaks
    -0.59
     fear
    -0.59
    ²¾
    -0.59
    POSITIVE LOGITS
    ield
    1.15
    onso
    1.11
    idav
    1.01
    ront
    1.00
    inia
    0.99
    irmation
    0.98
    inity
    0.98
    erences
    0.98
    alon
    0.96
    irms
    0.94
    Act Density 0.011%

    No Known Activations