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

    Neuronpedia

    INDEX
    Explanations

    instances of high-frequency punctuation marks and conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſtre
    -0.85
     cauſe
    -0.85
    SharedCtor
    -0.84
     houſe
    -0.80
     pleaſure
    -0.80
     leaſt
    -0.80
     Monfieur
    -0.79
     purpoſe
    -0.76
     betweenstory
    -0.75
     myſelf
    -0.73
    POSITIVE LOGITS
    ParallelGroup
    0.64
     ***!
    0.59
    SuppressLint
    0.58
    ORCID
    0.57
    WithMany
    0.56
    GraphicsUnit
    0.56
    AxisAlignment
    0.54
    VersionUID
    0.53
    providedIn
    0.53
     estimés
    0.52
    Act Density 0.166%

    No Known Activations