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

    Neuronpedia

    INDEX
    Explanations

    names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ober
    -0.70
    ively
    -0.68
    lich
    -0.67
    okin
    -0.67
     wrench
    -0.66
    ICES
    -0.65
    enegger
    -0.64
    ivity
    -0.63
     OPT
    -0.62
    ysis
    -0.62
    POSITIVE LOGITS
    zza
    0.87
    geon
    0.76
     Cheong
    0.75
    nesday
    0.74
    peria
    0.73
    ãĥ¼ãĤ¯
    0.71
    hiro
    0.71
    qua
    0.70
    æ©
    0.70
    venture
    0.70
    Act Density 0.050%

    No Known Activations