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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the progression of a situation or event over time

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the emergence or revelation of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heid
    -0.81
    ancies
    -0.74
     replacements
    -0.71
     replacement
    -0.70
     Replacement
    -0.69
    amiya
    -0.67
     resil
    -0.65
     Success
    -0.64
    phia
    -0.64
     monop
    -0.63
    POSITIVE LOGITS
     evident
    1.18
     apparent
    1.12
     clearer
    1.06
     manifest
    1.01
     clear
    0.98
     publicized
    0.97
     obvious
    0.97
     revealed
    0.94
     salient
    0.93
     headlines
    0.92
    Act Density 0.322%

    No Known Activations