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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á»ĥ
    -0.16
    983
    -0.15
    ouver
    -0.15
    hots
    -0.15
    vey
    -0.14
    972
    -0.14
    ancellor
    -0.14
    982
    -0.14
    629
    -0.14
    illez
    -0.14
    POSITIVE LOGITS
    izza
    0.14
    ackers
    0.13
    phia
    0.13
     Dod
    0.13
    ulo
    0.13
    vro
    0.13
    å½±åĵį
    0.13
    ÙĬار
    0.13
    iddi
    0.13
    ½
    0.12
    Act Density 0.058%

    No Known Activations