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

    Neuronpedia

    INDEX
    Explanations

    expressions related to providing assistance or ensuring proper handling of tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     demurrer
    -0.60
    Wax
    -0.55
    anyeol
    -0.55
     onCancelled
    -0.54
    ifero
    -0.53
    irited
    -0.52
    Anas
    -0.52
     intelligen
    -0.51
    énage
    -0.50
     conventionally
    -0.50
    POSITIVE LOGITS
    featureID
    0.76
    htë
    0.59
    IntoConstraints
    0.56
    UObject
    0.54
     riktig
    0.54
     szóci
    0.52
    StoryboardSegue
    0.52
     alltid
    0.51
     correcta
    0.51
     пожалуйста
    0.50
    Act Density 0.304%

    No Known Activations