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

    Neuronpedia

    INDEX
    Explanations

    long phrases or sentences related to technological processes or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to learning and processes involving time or stages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    %]
    -0.74
    ounding
    -0.71
    ums
    -0.68
    vana
    -0.63
    isu
    -0.62
    habi
    -0.62
    MOD
    -0.62
    resa
    -0.61
    instein
    -0.61
    egu
    -0.60
    POSITIVE LOGITS
     they
    1.13
     there
    1.00
     we
    0.99
     it
    0.95
     THEY
    0.92
     THERE
    0.88
     he
    0.87
    there
    0.82
    they
    0.82
     nobody
    0.81
    Act Density 0.571%

    No Known Activations