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

    Neuronpedia

    INDEX
    Explanations

    phrases and words concerning relationships and connections to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interop
    -0.18
    agement
    -0.16
    -toggler
    -0.15
    SES
    -0.14
    umble
    -0.14
    inz
    -0.13
    εβ
    -0.13
     Bald
    -0.13
    rior
    -0.13
     accident
    -0.13
    POSITIVE LOGITS
     directly
    0.20
     specifically
    0.19
    سÙĦاÙħ
    0.16
    äºİæĺ¯
    0.15
    ipse
    0.15
     пÑĢÑıмо
    0.15
     ther
    0.14
    specific
    0.14
    خاص
    0.14
    вÑĸд
    0.14
    Act Density 0.039%

    No Known Activations