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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating progress or growth in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bitwise
    -0.16
    undef
    -0.15
    élé
    -0.15
     thirst
    -0.14
    umer
    -0.14
    usch
    -0.14
    InView
    -0.14
    :numel
    -0.13
    esa
    -0.13
    ypo
    -0.13
    POSITIVE LOGITS
     shape
    0.31
     wings
    0.30
     currency
    0.30
     traction
    0.26
    currency
    0.26
     legs
    0.25
     weight
    0.25
     momentum
    0.24
     Currency
    0.24
    shape
    0.23
    Act Density 0.144%

    No Known Activations