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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.80
    хьтан
    -0.68
     $_[
    -0.67
     synap
    -0.66
     joaat
    -0.66
     gradova
    -0.64
     himſelf
    -0.64
    Vidite
    -0.63
    mybatisplus
    -0.63
     StyleSheet
    -0.63
    POSITIVE LOGITS
     else
    0.76
    else
    0.61
    Otherwise
    0.56
    Else
    0.56
    clyde
    0.55
    olare
    0.54
     come
    0.53
     Otherwise
    0.53
    toMatch
    0.53
     just
    0.52
    Act Density 0.028%

    No Known Activations