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

    Neuronpedia

    INDEX
    Explanations

    phrases related to calls for action or requests for attention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äħ
    -0.16
    eward
    -0.16
    rema
    -0.15
    andalone
    -0.15
    elyn
    -0.15
    ality
    -0.14
    esser
    -0.14
    dictions
    -0.13
    jal
    -0.13
    acock
    -0.13
    POSITIVE LOGITS
    igraphy
    0.21
    oused
    0.19
    istrovstvÃŃ
    0.17
     dib
    0.17
    IDO
    0.16
    stell
    0.16
    ameda
    0.15
    tight
    0.15
    macen
    0.15
    nap
    0.15
    Act Density 0.107%

    No Known Activations