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

    Neuronpedia

    INDEX
    Explanations

    words that indicate uncertainty or subjectivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adelphia
    -0.83
    anamo
    -0.77
     Horizons
    -0.77
    waukee
    -0.75
    iets
    -0.74
    iens
    -0.74
    xia
    -0.74
    uay
    -0.74
    ouses
    -0.73
    swick
    -0.72
    POSITIVE LOGITS
     alike
    0.82
     profitable
    0.79
     contradictory
    0.75
     camoufl
    0.74
     consequential
    0.73
     downright
    0.72
    -"
    0.72
     depend
    0.71
     fatal
    0.71
    )-
    0.71
    Act Density 0.097%

    No Known Activations