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

    Neuronpedia

    INDEX
    Explanations

    entries related to file types and server configurations

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to data management and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yss
    -0.73
    à¨
    -0.67
    姫
    -0.67
    asonable
    -0.67
    à©
    -0.65
    Scient
    -0.64
    rational
    -0.62
     Ples
    -0.62
    otropic
    -0.61
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.61
    POSITIVE LOGITS
    warts
    0.63
    ource
    0.61
    aret
    0.59
     XXX
    0.57
     dismant
    0.57
    ="#
    0.57
    ORTS
    0.57
     stationed
    0.57
     certified
    0.57
     Canter
    0.57
    Act Density 0.490%

    No Known Activations