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

    Neuronpedia

    INDEX
    Explanations

    keywords related to information or news reports, such as "On arrival," "There," "Just," "The," "What," etc

    oai_token-act-pair · gpt-3.5-turbo

    instances of introductory phrases or sentence openings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     �
    -0.73
    .)
    -0.67
     ''
    -0.63
    cum
    -0.61
     prompting
    -0.60
     ).
    -0.60
     Âł Âł Âł Âł
    -0.59
     listed
    -0.59
     .)
    -0.58
    ienne
    -0.58
    POSITIVE LOGITS
    withstanding
    1.10
    resa
    0.99
    ntil
    0.99
    chieve
    0.90
    %"
    0.89
    odore
    0.86
    ctions
    0.84
    "[
    0.81
    ircraft
    0.81
    xiety
    0.80
    Act Density 0.236%

    No Known Activations