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

    Neuronpedia

    INDEX
    Explanations

    terms related to magnets or magnetism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to magnets and buoyancy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ftime
    -0.81
     Extrem
    -0.75
    lly
    -0.72
    renheit
    -0.70
    pta
    -0.70
    اØ
    -0.69
    ntax
    -0.67
    chnology
    -0.66
    perture
    -0.66
    AKING
    -0.65
    POSITIVE LOGITS
    reys
    0.93
     magnet
    0.89
    oons
    0.87
    antic
    0.86
    antically
    0.85
    nets
    0.85
    itudes
    0.79
    ially
    0.78
    ancy
    0.78
    uncle
    0.77
    Act Density 0.024%

    No Known Activations