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

    Neuronpedia

    INDEX
    Explanations

    phrases containing instructions or points of interest

    oai_token-act-pair · gpt-3.5-turbo

    reference to projects, services, or products that require additional information or details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¶ħ
    -0.82
    efe
    -0.78
    lihood
    -0.73
    etheless
    -0.70
    eln
    -0.70
    itiz
    -0.67
    é¾įåĸļ士
    -0.66
    gling
    -0.66
    SpaceEngineers
    -0.65
    %-
    -0.65
    POSITIVE LOGITS
     visit
    1.41
     please
    1.40
     see
    1.30
     click
    1.30
     check
    1.25
     CLICK
    1.19
     consult
    1.18
     refer
    1.15
    please
    1.11
     subscribe
    1.09
    Act Density 0.115%

    No Known Activations