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

    Neuronpedia

    INDEX
    Explanations

    programming-related terminology and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    774
    -0.18
    inder
    -0.16
    öt
    -0.15
     rep
    -0.14
     Finger
    -0.14
     intr
    -0.14
     dist
    -0.14
    ade
    -0.14
     Tob
    -0.14
    zik
    -0.14
    POSITIVE LOGITS
    ombat
    0.17
    lesc
    0.17
    ces
    0.16
    .Solid
    0.15
    argo
    0.14
    alex
    0.14
    εια
    0.14
     ÙĪاس
    0.13
    CES
    0.13
    erald
    0.13
    Act Density 0.005%

    No Known Activations