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

    Neuronpedia

    INDEX
    Explanations

    terms related to computer programming and software development

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to design and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONSORED
    -0.75
    ibur
    -0.72
    beer
    -0.67
    hoe
    -0.66
     Rodham
    -0.66
    orship
    -0.66
    eport
    -0.65
     martyr
    -0.64
     endors
    -0.63
     abroad
    -0.63
    POSITIVE LOGITS
     arrays
    0.87
     folders
    0.87
     symmetry
    0.86
     grids
    0.85
    acters
    0.84
    Each
    0.83
     atoms
    0.83
     rearr
    0.83
     comma
    0.82
     partitions
    0.81
    Act Density 0.926%

    No Known Activations