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

    Neuronpedia

    INDEX
    Explanations

    references to the word "kind" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ional
    -0.17
    ĤŃ
    -0.16
    aches
    -0.15
    gov
    -0.15
    agon
    -0.15
    ors
    -0.15
    ponent
    -0.14
    ãģ£ãģ¡
    -0.14
    EF
    -0.14
    ampie
    -0.14
    POSITIVE LOGITS
    ergarten
    0.33
    red
    0.32
    reds
    0.25
    led
    0.23
    gom
    0.23
    ling
    0.23
    erg
    0.22
    ness
    0.19
    RED
    0.19
    -hearted
    0.18
    Act Density 0.034%

    No Known Activations