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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating receiving information or benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ianne
    -0.17
    oust
    -0.17
    benh
    -0.16
    YRO
    -0.16
    roads
    -0.15
    EMENT
    -0.14
    riminator
    -0.14
    зв
    -0.13
    uras
    -0.13
     dipped
    -0.13
    POSITIVE LOGITS
    ependency
    0.15
     occas
    0.15
     Loose
    0.15
    tin
    0.15
    ritt
    0.15
    leme
    0.15
    @$
    0.14
    CTR
    0.14
    endi
    0.13
    Sphere
    0.13
    Act Density 0.061%

    No Known Activations