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

    Neuronpedia

    INDEX
    Explanations

    time stamps written in the format of xx:xx

    oai_token-act-pair · gpt-3.5-turbo

    timestamps or time-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.88
    warts
    -0.83
     strugg
    -0.78
    jected
    -0.76
    attled
    -0.76
     disproportion
    -0.75
    omnia
    -0.74
    formation
    -0.73
    sole
    -0.73
    assic
    -0.72
    POSITIVE LOGITS
    mAh
    1.00
    00
    0.95
    --+
    0.92
    0100
    0.90
    MHz
    0.89
     NOTICE
    0.89
    âĢ³
    0.86
     UTC
    0.86
    nm
    0.84
    GMT
    0.84
    Act Density 0.025%

    No Known Activations