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

    Neuronpedia

    INDEX
    Explanations

    words related to assumptions and presumptions

    oai_token-act-pair · gpt-3.5-turbo

    words related to assumptions and expectations about situations or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oho
    -0.73
    OTOS
    -0.69
    erry
    -0.64
     Hunting
    -0.64
     Clubs
    -0.64
     Farn
    -0.64
     Club
    -0.63
    Eva
    -0.63
    foreseen
    -0.62
    artney
    -0.62
    POSITIVE LOGITS
     presum
    0.94
     presumption
    0.91
     assum
    0.83
     assume
    0.79
    lessly
    0.79
     presume
    0.79
     fide
    0.78
     infall
    0.77
     assumption
    0.75
    cipled
    0.74
    Act Density 0.010%

    No Known Activations