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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "apart."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gear
    -0.17
    erable
    -0.16
    presso
    -0.16
    erton
    -0.16
    cretion
    -0.15
    otlin
    -0.15
    ertz
    -0.15
    niest
    -0.15
    agers
    -0.14
    ayah
    -0.14
    POSITIVE LOGITS
    icular
    0.27
    icip
    0.23
    icipant
    0.22
    icipation
    0.22
    icularly
    0.21
    ments
    0.21
    ures
    0.19
    theid
    0.18
    amento
    0.18
    ness
    0.17
    Act Density 0.009%

    No Known Activations