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

    Neuronpedia

    INDEX
    Explanations

    unusual or unexpected punctuation and symbols within text

    oai_token-act-pair · gpt-3.5-turbo

    question marks and exclamation points indicating rhetorical or dramatic punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rogen
    -0.71
    romy
    -0.71
    rament
    -0.70
    estation
    -0.70
    ral
    -0.67
    oria
    -0.64
    rab
    -0.64
    ©¶æ
    -0.63
    zbollah
    -0.62
    urally
    -0.62
    POSITIVE LOGITS
    ominated
    0.74
     srfAttach
    0.69
    okers
    0.67
    ittens
    0.66
    uits
    0.66
    CLASSIFIED
    0.65
    catentry
    0.64
    hops
    0.64
    aucuses
    0.64
    ategory
    0.63
    Act Density 0.035%

    No Known Activations