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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate subsequent actions or developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     retire
    -0.60
     Dispose
    -0.60
     etik
    -0.59
    alpin
    -0.57
    jsonwebtoken
    -0.57
     olvides
    -0.55
     kim
    -0.54
     Mure
    -0.53
    hok
    -0.53
    pek
    -0.53
    POSITIVE LOGITS
     Following
    2.41
     following
    2.38
    Following
    2.35
    following
    2.31
     FOLLOWING
    2.11
     folgenden
    1.36
     følgende
    1.22
     seguinte
    1.21
     seguente
    1.18
     siguientes
    1.18
    Act Density 0.189%

    No Known Activations