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

    Neuronpedia

    INDEX
    Explanations

    structural elements, punctuation, and transitions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ritch
    -0.16
    uzzi
    -0.16
    istar
    -0.15
    Initialize
    -0.14
    ç³
    -0.14
    ugg
    -0.14
     cultivated
    -0.14
     cultivation
    -0.13
    ckill
    -0.13
    ingly
    -0.13
    POSITIVE LOGITS
     Making
    0.26
     Meeting
    0.24
     Dro
    0.23
     Using
    0.23
     Setting
    0.23
     Opening
    0.23
     Att
    0.22
     Taking
    0.22
     Comple
    0.22
     Align
    0.22
    Act Density 0.309%

    No Known Activations