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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments regarding interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤīãģı
    -0.15
    (éĩij
    -0.15
     SvÄĽt
    -0.15
    ngen
    -0.14
    -shift
    -0.14
    bons
    -0.14
     ceil
    -0.14
     ÑģоÑĤÑĢÑĥд
    -0.14
    shift
    -0.14
     shift
    -0.14
    POSITIVE LOGITS
     Bachelor
    0.34
    Bachelor
    0.31
     bachelor
    0.27
     Bach
    0.26
     bach
    0.25
     ABC
    0.25
     elim
    0.24
    ABC
    0.22
     Fantasy
    0.22
    ometown
    0.21
    Act Density 0.002%

    No Known Activations