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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal emotions and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ľ
    -0.15
     Shed
    -0.15
    bin
    -0.15
    ضÙĬ
    -0.15
     already
    -0.14
    lan
    -0.14
    lon
    -0.14
    Marsh
    -0.14
    alous
    -0.14
    already
    -0.14
    POSITIVE LOGITS
     notices
    0.17
     keyed
    0.16
     concern
    0.16
     notice
    0.16
    缺
    0.16
     excel
    0.16
    Äįil
    0.16
    zza
    0.15
     lacked
    0.15
     dimensional
    0.14
    Act Density 0.112%

    No Known Activations