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

    Neuronpedia

    INDEX
    Explanations

    statements expressing a call to action or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    instances of introductory phrases indicating personal perspective or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     goto
    -0.72
    CVE
    -0.67
     bladder
    -0.64
     RTX
    -0.59
     Vita
    -0.57
     Reef
    -0.57
     nap
    -0.56
     mercury
    -0.56
     LV
    -0.55
    ãģŁ
    -0.55
    POSITIVE LOGITS
    anmar
    0.99
    odore
    0.86
    jriwal
    0.80
    ulty
    0.78
     prosec
    0.78
    intendent
    0.76
    foundland
    0.76
    htaking
    0.76
    anyahu
    0.76
    initely
    0.73
    Act Density 0.187%

    No Known Activations