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

    Neuronpedia

    INDEX
    Explanations

    phrases related to lack of awareness or knowledge

    oai_token-act-pair · gpt-3.5-turbo

    terms related to lack of awareness or ignorance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emetery
    -0.81
    gran
    -0.76
    ickr
    -0.74
    artney
    -0.73
    ramid
    -0.71
    ccording
    -0.66
    addafi
    -0.65
    uilding
    -0.65
    hetti
    -0.59
    Contents
    -0.58
    POSITIVE LOGITS
    ness
    1.08
    NESS
    0.94
    ingly
    0.92
    ledge
    0.87
    theless
    0.85
    ewater
    0.82
    nesses
    0.81
     Leilan
    0.78
    uania
    0.77
    icity
    0.77
    Act Density 0.026%

    No Known Activations