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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the notion of "all" or totality in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GIVEREF
    -0.81
     kautta
    -0.73
     myſelf
    -0.71
    setopt
    -0.71
     Silurian
    -0.70
    RTLD
    -0.67
    ſelves
    -0.67
    tersebut
    -0.66
    хьтан
    -0.65
    oredCriteria
    -0.65
    POSITIVE LOGITS
     ведь
    0.75
    ведь
    0.73
    畢竟
    0.72
     hey
    0.71
     przecież
    0.70
    毕竟
    0.66
     what
    0.65
     Ведь
    0.64
     aren
    0.62
     living
    0.59
    Act Density 0.102%

    No Known Activations