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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and constructs

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ſelf
    -0.81
     كومونز
    -0.74
     unſ
    -0.74
    adpleegd
    -0.73
     Jefus
    -0.73
     kaarangay
    -0.73
     Cæsar
    -0.72
     faſt
    -0.71
     Perſ
    -0.70
     ſche
    -0.69
    POSITIVE LOGITS
     wakil
    0.49
     Sweeney
    0.49
    +");
    0.48
    '));
    0.46
    LogFactory
    0.46
    כי
    0.45
     k
    0.44
     Ch
    0.44
    gangen
    0.44
    グラフ
    0.43
    Act Density 0.153%

    No Known Activations