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

    Neuronpedia

    INDEX
    Explanations

    phrases containing "black-and-white"

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.82
    ancial
    -0.78
    zynski
    -0.71
    odcast
    -0.67
    ULTS
    -0.66
    hower
    -0.64
    urry
    -0.61
     Mercenary
    -0.60
    edom
    -0.60
     Examiner
    -0.59
    POSITIVE LOGITS
    romeda
    1.15
    rew
    0.95
    inav
    0.80
    hra
    0.77
    aji
    0.74
    rolet
    0.74
    rogen
    0.73
     therefore
    0.73
     consequently
    0.72
    zbollah
    0.70
    Act Density 0.029%

    No Known Activations