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

    Neuronpedia

    INDEX
    Explanations

    sentences indicating disapproval or criticism

    oai_token-act-pair · gpt-3.5-turbo

    expressions of rejection or disapproval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenberg
    -0.85
     bottleneck
    -0.72
    umping
    -0.70
    umped
    -0.68
     clut
    -0.67
     looms
    -0.64
    ©¶æ¥µ
    -0.64
    moil
    -0.64
    rolled
    -0.64
    azard
    -0.64
    POSITIVE LOGITS
     acceptable
    1.11
     decency
    1.09
    acceptable
    1.07
     sane
    0.99
     civilized
    0.99
    ensible
    0.98
     condone
    0.93
     patriotism
    0.93
     credible
    0.92
     lawful
    0.92
    Act Density 0.386%

    No Known Activations