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

    Neuronpedia

    INDEX
    Explanations

    phrases related to things that stand out or are unique

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating something that is distinctive or prominent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elf
    -0.91
    ummer
    -0.74
     lockout
    -0.67
     confir
    -0.66
     typo
    -0.64
    itamin
    -0.64
    ettlement
    -0.62
    ourse
    -0.61
    ternal
    -0.61
    ynchron
    -0.60
    POSITIVE LOGITS
     amongst
    1.08
     among
    0.94
     prominently
    0.85
     conspic
    0.83
     brightly
    0.81
    box
    0.77
    ocl
    0.76
     visually
    0.75
     Flavoring
    0.74
    comings
    0.73
    Act Density 0.043%

    No Known Activations