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

    Neuronpedia

    INDEX
    Explanations

    phrases and words indicating a mix of criticism and praise towards artistic or cultural products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akis
    -0.17
    enberg
    -0.16
    rieb
    -0.16
    entai
    -0.15
    ddy
    -0.14
    ulty
    -0.14
    iber
    -0.14
     McInt
    -0.14
     Priv
    -0.14
    reff
    -0.14
    POSITIVE LOGITS
    ãĥĥãĤ«ãĥ¼
    0.16
    Bindable
    0.15
    åĺĽ
    0.14
    aison
    0.13
     oku
    0.13
    inance
    0.13
    etros
    0.13
    chner
    0.13
    _FMT
    0.13
     XK
    0.13
    Act Density 0.401%

    No Known Activations