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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing unusual or unexpected experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scope
    -0.14
    .fetch
    -0.14
     ακ
    -0.13
     ÑĤоÑĩно
    -0.13
    िष
    -0.13
    ÏĥÏĢ
    -0.13
     Shadows
    -0.13
     thro
    -0.13
    POCH
    -0.13
    roupe
    -0.13
    POSITIVE LOGITS
    cplusplus
    0.14
    kop
    0.14
    stype
    0.14
    pll
    0.14
    pery
    0.14
    isors
    0.14
    installer
    0.13
    ÙĪزÙĩ
    0.13
     pole
    0.13
    uti
    0.13
    Act Density 0.178%

    No Known Activations