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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the root word "mut" and its variations, suggesting a focus on themes of change or alteration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oze
    -0.18
    çĸ¾
    -0.17
    bjerg
    -0.16
    otte
    -0.16
    irsch
    -0.15
    ettel
    -0.15
    croll
    -0.15
    ç´Ļ
    -0.15
    endir
    -0.14
    getter
    -0.14
    POSITIVE LOGITS
    ual
    0.29
    iple
    0.26
    ually
    0.25
    inous
    0.25
    iny
    0.24
    agen
    0.24
    uality
    0.23
    ational
    0.22
    tering
    0.22
    UAL
    0.21
    Act Density 0.009%

    No Known Activations