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

    Neuronpedia

    INDEX
    Explanations

    phrases related to acceptance or approval in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ·ãĥ§ãĥ³
    -0.15
    tel
    -0.14
    ERSHEY
    -0.14
    aliz
    -0.14
    uffles
    -0.14
    okol
    -0.14
    734
    -0.14
     Lans
    -0.13
    allow
    -0.13
    Ãł
    -0.13
    POSITIVE LOGITS
     Seb
    0.14
     Robbie
    0.14
    Winvalid
    0.14
    ijk
    0.14
     å¾Ĵ
    0.14
    ivist
    0.13
    _viewer
    0.13
    ekk
    0.13
    (éĩij
    0.13
    ahl
    0.13
    Act Density 0.020%

    No Known Activations