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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to significant impact or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mess
    -0.17
    Mess
    -0.17
    mess
    -0.16
    asaki
    -0.15
    antha
    -0.14
    icorn
    -0.14
    blas
    -0.14
    ÑĢоÑĩ
    -0.14
    ÙģتÙĩ
    -0.14
    lene
    -0.14
    POSITIVE LOGITS
    OMPI
    0.17
     Hills
    0.14
    igne
    0.14
    propri
    0.14
     Chase
    0.13
    omain
    0.13
    enu
    0.13
     Dod
    0.13
     dit
    0.13
    _interest
    0.13
    Act Density 0.049%

    No Known Activations