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

    Neuronpedia

    INDEX
    Explanations

    pronouns and verbs, indicating personal connections or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jang
    -0.17
    -instagram
    -0.15
    zilla
    -0.15
    kud
    -0.14
     CONTR
    -0.14
     GFX
    -0.14
    मर
    -0.14
    arnings
    -0.14
    assen
    -0.13
    令
    -0.13
    POSITIVE LOGITS
     Notice
    0.17
     happens
    0.16
     notice
    0.16
     Fisher
    0.16
    ove
    0.15
    ย
    0.15
    ãĤ¤ãĤ¯
    0.15
    endor
    0.15
     happen
    0.15
    ja
    0.15
    Act Density 0.009%

    No Known Activations