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

    Neuronpedia

    INDEX
    Explanations

    words indicating uncertainty or hesitation

    oai_token-act-pair · gpt-3.5-turbo

    informal qualifiers expressing a degree of mediocrity or dissatisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    worthiness
    -1.00
    lain
    -0.94
    enance
    -0.82
    iens
    -0.79
    heid
    -0.76
    worthy
    -0.74
    atars
    -0.73
    upon
    -0.72
    HCR
    -0.71
    imentary
    -0.69
    POSITIVE LOGITS
     darn
    1.00
     kinda
    0.97
     dunno
    0.81
     weird
    0.79
     shit
    0.78
     damn
    0.78
     silly
    0.75
    nect
    0.75
     bu
    0.73
     thing
    0.73
    Act Density 0.016%

    No Known Activations