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

    Neuronpedia

    INDEX
    Explanations

    words and phrases expressing strong opinions or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     feeling
    -0.19
     being
    -0.16
    WK
    -0.16
    .GraphicsUnit
    -0.16
    odelist
    -0.15
    etadata
    -0.15
    ska
    -0.15
    _translate
    -0.14
     Ø´Ùħ
    -0.14
    .uml
    -0.14
    POSITIVE LOGITS
     fond
    0.28
     Fond
    0.23
     partial
    0.22
     fans
    0.21
     Fans
    0.20
    partial
    0.19
    neutral
    0.18
    fans
    0.18
     neutral
    0.17
     attached
    0.17
    Act Density 0.023%

    No Known Activations