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

    Neuronpedia

    INDEX
    Explanations

    key concepts related to simplicity and practical advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ANGO
    -0.16
    ango
    -0.15
    ambio
    -0.14
    åĶ¯
    -0.14
    alph
    -0.14
    aving
    -0.14
    omp
    -0.13
     inf
    -0.13
    ỡ
    -0.13
    .cx
    -0.13
    POSITIVE LOGITS
    irts
    0.16
    -Smith
    0.15
    ndef
    0.14
     пеÑĢеÑĢ
    0.14
    ruta
    0.13
    @mail
    0.13
    ¢
    0.13
    759
    0.13
     YYS
    0.13
    @email
    0.13
    Act Density 0.140%

    No Known Activations