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

    Neuronpedia

    INDEX
    Explanations

    strings or sequences that are empty or contain specific repeated characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ••••
    -0.61
    =".
    -0.61
    </b>
    -0.59
    aarrggbb
    -0.56
    </i>
    -0.55
    "]="
    -0.54
    "
    -0.53
    coledì
    -0.53
     endblock
    -0.52
    fø
    -0.52
    POSITIVE LOGITS
    1.09
     ""
    0.97
    )
    0.92
     "")
    0.91
    ⓧ
    0.89
     "")
    0.86
    ""
    0.83
    =""
    0.79
     Roskov
    0.79
     ""){
    0.78
    Act Density 0.345%

    No Known Activations