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

    Neuronpedia

    INDEX
    Explanations

    words related to harassment or negative behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieux
    -0.15
    obo
    -0.14
    enido
    -0.14
    sob
    -0.14
    earn
    -0.14
    EntityType
    -0.14
    orners
    -0.14
    chant
    -0.14
    Enums
    -0.14
    obil
    -0.13
    POSITIVE LOGITS
    hoe
    0.18
    isle
    0.17
    ilton
    0.16
    odge
    0.16
    à¹īย
    0.16
    ley
    0.15
    .AddItem
    0.15
    BYTES
    0.15
    ufe
    0.15
    icio
    0.14
    Act Density 0.021%

    No Known Activations