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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe the process of transforming ideas or materials into coherent and organized forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akan
    -0.16
    athan
    -0.15
     -------------------------------------------------------------------------
    -0.14
    lfw
    -0.14
     Gir
    -0.14
     candles
    -0.14
    ajan
    -0.14
    atte
    -0.13
    mem
    -0.13
    issa
    -0.13
    POSITIVE LOGITS
    ynom
    0.15
    uchs
    0.15
    onto
    0.15
    unnel
    0.15
    fila
    0.15
    ingleton
    0.14
    ournaments
    0.14
    ,eg
    0.14
    LOY
    0.14
    uch
    0.14
    Act Density 0.164%

    No Known Activations