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

    Neuronpedia

    INDEX
    Explanations

    phrases related to law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "new."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suspic
    -0.67
    Reloaded
    -0.64
     NAACP
    -0.61
     dissu
    -0.58
     Vance
    -0.58
    ________________________
    -0.57
     Reconstruction
    -0.57
    ................................................................
    -0.57
     Duchess
    -0.57
     Monteneg
    -0.56
    POSITIVE LOGITS
    riter
    1.43
    ritten
    1.40
    ords
    1.30
    estern
    1.27
    orth
    1.25
    isdom
    1.23
    idth
    1.20
    ITNESS
    1.19
    olf
    1.19
    alker
    1.18
    Act Density 0.044%

    No Known Activations