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

    Neuronpedia

    INDEX
    Explanations

    themes related to interpersonal treatment and behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eker
    -0.15
    avra
    -0.15
     readily
    -0.15
    Whats
    -0.14
    uce
    -0.14
    ucha
    -0.14
    (EFFECT
    -0.14
     gee
    -0.13
    kle
    -0.13
     reliably
    -0.13
    POSITIVE LOGITS
     differently
    0.54
     like
    0.29
    iffer
    0.26
     accordingly
    0.23
     incorrectly
    0.22
    наÑĩе
    0.22
     diffé
    0.21
     according
    0.21
     Like
    0.21
     пÑĢавилÑĮно
    0.21
    Act Density 0.412%

    No Known Activations