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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating rankings or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kowski
    -0.15
    antine
    -0.15
    zi
    -0.14
    DOC
    -0.14
     rang
    -0.14
    à¥Ģà¤Ł
    -0.14
     fif
    -0.14
    hung
    -0.14
    hattan
    -0.13
    .mdl
    -0.13
    POSITIVE LOGITS
    åį«
    0.16
    erece
    0.15
    unfold
    0.14
    égor
    0.14
    anel
    0.14
    è¡Ľ
    0.14
    HEAD
    0.14
    erring
    0.13
    upon
    0.13
    ç±³
    0.13
    Act Density 0.020%

    No Known Activations