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

    Neuronpedia

    INDEX
    Explanations

    names and titles related to notable individuals, places, or cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _MALLOC
    -0.17
    ccoli
    -0.15
    -guard
    -0.15
     granite
    -0.15
    astos
    -0.14
    ancel
    -0.14
     Claus
    -0.14
    gram
    -0.14
    vale
    -0.14
     gram
    -0.14
    POSITIVE LOGITS
     Barrett
    0.16
    ivec
    0.16
    ive
    0.14
    ived
    0.14
    äl
    0.14
    hart
    0.14
     rež
    0.13
    ouser
    0.13
    ivity
    0.13
    .observe
    0.13
    Act Density 0.007%

    No Known Activations