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

    Neuronpedia

    INDEX
    Explanations

    references to overall assessments or evaluations of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eyse
    -0.17
    ãn
    -0.17
    imals
    -0.16
    ess
    -0.16
    вÑĢоп
    -0.16
    essler
    -0.15
    ourke
    -0.15
    apult
    -0.15
    äge
    -0.15
    burg
    -0.15
    POSITIVE LOGITS
    ingham
    0.23
    igator
    0.21
    mente
    0.20
    most
    0.19
    -purpose
    0.15
    lsru
    0.15
    iese
    0.15
    ready
    0.15
    dehyde
    0.14
    Ħìŀ¬
    0.14
    Act Density 0.013%

    No Known Activations