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

    Neuronpedia

    INDEX
    Explanations

    instances of introductory phrases that establish the nature or type of the subject being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äĩ
    -0.16
    ãĥĭãĥ¼
    -0.16
    zos
    -0.15
    _pf
    -0.14
     Conservation
    -0.14
    úc
    -0.14
    EPHIR
    -0.14
     Princip
    -0.14
    ifice
    -0.14
    ãĥ©ãĥ³ãĤ¹
    -0.14
    POSITIVE LOGITS
    ector
    0.17
    ombat
    0.15
    linky
    0.15
    ubu
    0.15
    EMPTY
    0.15
    AGES
    0.15
    eterangan
    0.15
    abbo
    0.14
    Detach
    0.14
    etzt
    0.14
    Act Density 0.049%

    No Known Activations