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

    Neuronpedia

    INDEX
    Explanations

    instances of the number "two" being mentioned in textual context

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities or numerical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    matter
    -0.85
    cca
    -0.67
    Ĥ
    -0.64
    Gene
    -0.64
    don
    -0.64
    Mas
    -0.62
    Kar
    -0.61
     Akin
    -0.61
    Mos
    -0.61
    Barn
    -0.61
    POSITIVE LOGITS
     hemisphere
    0.78
     quir
    0.75
     Flavoring
    0.72
    acea
    0.71
     certs
    0.70
    itol
    0.70
     subp
    0.70
     favorites
    0.69
    icho
    0.68
    idad
    0.66
    Act Density 0.093%

    No Known Activations