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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sponsorship, technology, and pop culture references

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks indicating questions and exclamations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    YL
    -0.70
    ral
    -0.68
    verbs
    -0.66
    zbollah
    -0.66
    worldly
    -0.66
    ©¶æ
    -0.64
    rab
    -0.63
    bas
    -0.60
    romy
    -0.60
    ding
    -0.59
    POSITIVE LOGITS
    ominated
    0.75
    uits
    0.73
    uly
    0.71
    ordable
    0.67
    ugg
    0.67
     Flavoring
    0.67
    aucuses
    0.66
    CLASSIFIED
    0.65
    ittens
    0.65
    theless
    0.65
    Act Density 0.032%

    No Known Activations