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

    Neuronpedia

    INDEX
    Explanations

    words related to intervention or interference

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of projects or interjections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.69
    tnc
    -0.68
    sem
    -0.66
     Kinnikuman
    -0.66
    é¾įåĸļ士
    -0.64
    MpServer
    -0.64
    ISC
    -0.64
    ¯¯¯¯¯¯¯¯
    -0.63
    ©¶æ
    -0.62
    Ô
    -0.61
    POSITIVE LOGITS
    ject
    1.05
    ions
    0.95
    urous
    0.90
    ures
    0.84
    ulous
    0.82
    culosis
    0.81
    ierrez
    0.80
    jection
    0.79
    otomy
    0.78
    ossal
    0.78
    Act Density 0.008%

    No Known Activations