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

    Neuronpedia

    INDEX
    Explanations

    the length of strings in code

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Sodom
    -0.75
     bouch
    -0.69
     Parac
    -0.68
     Eury
    -0.68
     Joss
    -0.68
     åt
    -0.66
     Phry
    -0.65
    人形
    -0.65
     parlour
    -0.64
     Sarg
    -0.64
    POSITIVE LOGITS
     strlen
    1.36
    strlen
    1.21
    cstring
    0.72
    terness
    0.68
    <!--[
    0.63
     @"/
    0.63
    vron
    0.62
    "],
    0.62
    eqn
    0.61
    "]),
    0.60
    Act Density 0.000%

    No Known Activations