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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time spent and duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.63
     hivyo
    -0.54
     ossia
    -0.52
     namelijk
    -0.50
     بتاريخ
    -0.48
     سوی
    -0.48
    endif
    -0.47
     kursi
    -0.47
     للمعارف
    -0.46
     stimmt
    -0.45
    POSITIVE LOGITS
     dozen
    0.99
    dozen
    0.83
     dizaine
    0.82
    五六
    0.77
     half
    0.76
     five
    0.73
    七八
    0.73
     halfway
    0.73
     fifteen
    0.72
    half
    0.72
    Act Density 0.237%

    No Known Activations