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

    Neuronpedia

    INDEX
    Explanations

    expressions of fondness or affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.24
    erif
    -0.17
    edList
    -0.16
    erre
    -0.16
    orgot
    -0.16
    erde
    -0.16
    icus
    -0.15
    ãĥ¼ãĥ©
    -0.15
    erse
    -0.15
    orsch
    -0.14
    POSITIVE LOGITS
    amental
    0.30
    ue
    0.28
    ness
    0.27
    amentals
    0.21
    ly
    0.20
    ament
    0.19
    NESS
    0.19
    ling
    0.17
    azione
    0.17
    amenti
    0.17
    Act Density 0.007%

    No Known Activations