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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to conditional logic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iprot
    -0.44
    argc
    -0.44
    iper
    -0.43
    vel
    -0.43
    ahua
    -0.42
    zä
    -0.42
    htar
    -0.41
    uremberg
    -0.41
    werk
    -0.40
     Arxiv
    -0.40
    POSITIVE LOGITS
     otherwise
    2.99
     Otherwise
    2.87
    Otherwise
    2.82
    otherwise
    2.70
     else
    2.45
     OTHERWISE
    2.40
     altrimenti
    2.37
    else
    2.23
     Else
    2.16
     ellers
    2.04
    Act Density 0.233%

    No Known Activations