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

    Neuronpedia

    INDEX
    Explanations

    terminology related to scientific experiments and research

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ferm" and its variations, indicating a focus on a specific scientific topic related to fermions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vati
    -0.84
    ched
    -0.75
     stake
    -0.68
    handled
    -0.66
    verted
    -0.65
    ciating
    -0.64
    verts
    -0.64
    nings
    -0.63
    ============
    -0.63
    figure
    -0.61
    POSITIVE LOGITS
    aceutical
    0.90
    ilk
    0.88
    obile
    0.84
    asonic
    0.84
    ont
    0.82
    otor
    0.79
    uda
    0.78
    issions
    0.78
    andom
    0.77
    ission
    0.77
    Act Density 0.014%

    No Known Activations