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

    Neuronpedia

    INDEX
    Explanations

    negative statements or expressions of doubt or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atern
    -0.17
    ayd
    -0.14
    бÑĥÑĤ
    -0.14
    ÌĨ
    -0.13
    __/
    -0.13
    ursor
    -0.13
    ries
    -0.13
    .dx
    -0.13
    inski
    -0.13
    istra
    -0.13
    POSITIVE LOGITS
    aleigh
    0.17
    erif
    0.15
    oger
    0.15
    aket
    0.15
    viar
    0.14
    tery
    0.14
    ¼
    0.14
    _guid
    0.14
    ìį¨
    0.14
    estic
    0.13
    Act Density 0.102%

    No Known Activations