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

    Neuronpedia

    INDEX
    Explanations

    phrases related to politics

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     advis
    -0.71
     dotted
    -0.67
     applicable
    -0.63
     theoret
    -0.60
     chopping
    -0.60
     confidentiality
    -0.60
     wise
    -0.59
    olation
    -0.58
     imposition
    -0.58
    iture
    -0.58
    POSITIVE LOGITS
    Va
    1.03
    Skill
    0.98
    E
    0.91
    O
    0.90
    A
    0.90
    J
    0.88
    AX
    0.87
    Ire
    0.82
    C
    0.82
    S
    0.80
    Act Density 0.070%

    No Known Activations