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

    Neuronpedia

    INDEX
    Explanations

    people or things that are physically close to each other

    oai_token-act-pair · gpt-3.5-turbo

    references to close relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ICAN
    -0.89
    AIN
    -0.69
    onso
    -0.68
    mA
    -0.67
    ican
    -0.67
    NZ
    -0.66
     Pengu
    -0.65
    Ø©
    -0.65
    çīĪ
    -0.65
    Sov
    -0.64
    POSITIVE LOGITS
     minded
    0.98
     proximity
    0.93
    sighted
    0.86
     confinement
    0.83
    minded
    0.81
     confid
    0.81
     enough
    0.76
     doors
    0.76
    ups
    0.76
    paren
    0.76
    Act Density 0.029%

    No Known Activations