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

    Neuronpedia

    INDEX
    Explanations

    actions or activities that convey strong emotional expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yms
    -0.17
    ciler
    -0.17
     anale
    -0.16
    ncia
    -0.15
    yro
    -0.15
    tae
    -0.14
    ycop
    -0.14
    xea
    -0.14
    quires
    -0.14
    eon
    -0.14
    POSITIVE LOGITS
    fur
    0.21
     Newman
    0.19
     Fur
    0.18
     fur
    0.16
    idi
    0.15
     Peters
    0.15
     Baba
    0.15
     j
    0.14
    '])?
    0.14
    +-+-+-+-
    0.14
    Act Density 0.000%

    No Known Activations