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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and conditional probabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rms
    -0.07
    IU
    -0.07
    pert
    -0.07
    fony
    -0.07
    iç
    -0.07
    çĮľ
    -0.07
    ezi
    -0.07
    ANGLE
    -0.07
    -thumbnails
    -0.07
     GenerationType
    -0.07
    POSITIVE LOGITS
     probability
    0.09
     likelihood
    0.07
    ute
    0.07
     probabilities
    0.07
     odds
    0.07
     Probability
    0.07
    _probs
    0.06
    ite
    0.06
     events
    0.06
    px
    0.06
    Act Density 0.019%

    No Known Activations