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

    Neuronpedia

    INDEX
    Explanations

    numeric and alphanumeric values, as well as their structured representations in code or data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     charge
    -0.17
     swept
    -0.15
     st
    -0.15
     picking
    -0.15
    :
    -0.15
     h
    -0.15
    pace
    -0.14
     Sweep
    -0.14
    847
    -0.14
     chief
    -0.14
    POSITIVE LOGITS
    arella
    0.17
    SCII
    0.16
    erken
    0.16
    /stretch
    0.16
    isha
    0.16
    IRA
    0.15
    ãĥªãĥ³
    0.15
    /autoload
    0.15
     corrid
    0.15
     наÑĤÑĥ
    0.15
    Act Density 0.045%

    No Known Activations