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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to manipulation and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    068
    -0.16
    atik
    -0.15
    åı·
    -0.14
     autos
    -0.14
    ember
    -0.14
     Zem
    -0.14
    alf
    -0.14
     Shame
    -0.14
    inar
    -0.14
    ÙĪار
    -0.14
    POSITIVE LOGITS
    uela
    0.25
    tras
    0.23
    ually
    0.22
    iac
    0.21
    ual
    0.20
    uelle
    0.20
    ifold
    0.19
    ulative
    0.19
    uales
    0.18
    resa
    0.17
    Act Density 0.034%

    No Known Activations