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

    Neuronpedia

    INDEX
    Explanations

    phrases related to having only one choice or option

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing exclusivity or singularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    insula
    -0.79
    finder
    -0.72
     belie
    -0.69
    align
    -0.68
     charism
    -0.65
     reborn
    -0.65
     largeDownload
    -0.61
    dict
    -0.60
    multipl
    -0.59
     anytime
    -0.58
    POSITIVE LOGITS
     marginally
    0.84
     scratches
    0.78
    ifiable
    0.74
     minor
    0.73
     ONE
    0.72
    ICES
    0.72
    oor
    0.68
    ices
    0.68
     curs
    0.68
     scratched
    0.67
    Act Density 0.062%

    No Known Activations