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

    Neuronpedia

    INDEX
    Explanations

    words related to secretive or covert actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "trauma" or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensor
    -0.71
    hyde
    -0.71
     Mellon
    -0.68
    ãģ®éŃĶ
    -0.67
    ENSE
    -0.67
    ensable
    -0.64
    ifference
    -0.63
    RIC
    -0.63
    ensation
    -0.62
     Mechdragon
    -0.59
    POSITIVE LOGITS
    pez
    1.01
    tro
    0.92
    ppings
    0.89
    inen
    0.88
     tra
    0.87
    ph
    0.87
    ger
    0.84
    izoph
    0.83
    gers
    0.81
    itors
    0.78
    Act Density 0.016%

    No Known Activations