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

    Neuronpedia

    INDEX
    Explanations

    words that express speculation or assumption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.55
    typeorm
    -0.52
    ConstraintMaker
    -0.51
     propOrder
    -0.49
    PyExc
    -0.47
     autorytatywna
    -0.47
    concentr
    -0.47
    тьяна
    -0.47
    abetes
    -0.47
     vermis
    -0.46
    POSITIVE LOGITS
    umably
    0.85
     presumably
    0.84
    presumably
    0.72
     Presumably
    0.69
     hopefully
    0.66
    Hopefully
    0.65
     conceivably
    0.65
    hopefully
    0.63
     potentially
    0.61
    Ideally
    0.61
    Act Density 0.607%

    No Known Activations