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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "among" and its variations, indicating a focus on group or collective contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ising
    -0.17
    aries
    -0.17
    itz
    -0.16
    eri
    -0.15
    burg
    -0.15
    orsch
    -0.14
    ential
    -0.14
    eros
    -0.14
    osit
    -0.13
    oca
    -0.13
    POSITIVE LOGITS
    st
    0.36
     those
    0.21
     Equals
    0.20
     equals
    0.20
     Ñģобой
    0.20
    sted
    0.19
    est
    0.19
    s
    0.19
     пÑĢоÑĩ
    0.18
     themselves
    0.18
    Act Density 0.033%

    No Known Activations