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

    Neuronpedia

    INDEX
    Explanations

    the special character Ċ used as a marker

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to emotional expressions and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ptions
    -0.72
    ÄŁ
    -0.68
    imov
    -0.64
    backer
    -0.64
    agy
    -0.62
     extr
    -0.62
    arding
    -0.61
     decentral
    -0.61
    icer
    -0.59
     decom
    -0.59
    POSITIVE LOGITS
     Where
    0.88
    And
    0.85
     Who
    0.82
    Unt
    0.81
    ORN
    0.80
    Which
    0.80
     Shall
    0.79
     Waiting
    0.77
     Surely
    0.76
    Cause
    0.75
    Act Density 0.131%

    No Known Activations