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

    Neuronpedia

    INDEX
    Explanations

    language associated with teamwork and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BOR
    -0.15
    iller
    -0.15
    Pretty
    -0.15
     awakeFromNib
    -0.15
    [this
    -0.15
     Pretty
    -0.14
    [][
    -0.14
    виÑĩай
    -0.14
    ìĬ¤íĬ¸
    -0.14
    Modifier
    -0.14
    POSITIVE LOGITS
     sort
    0.23
     actually
    0.20
     sorts
    0.17
    sort
    0.17
    bearing
    0.16
     then
    0.15
     bits
    0.15
     yeah
    0.15
     Bearing
    0.15
    actually
    0.15
    Act Density 0.004%

    No Known Activations