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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to actions or characteristics related to people and groups

    oai_token-act-pair · gpt-3.5-turbo

    pronouns that refer to people or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Darling
    -0.66
    mi
    -0.60
    kamp
    -0.59
    zu
    -0.58
    Quantity
    -0.58
    erenn
    -0.58
    mini
    -0.57
    aleb
    -0.56
    oji
    -0.56
    dim
    -0.56
    POSITIVE LOGITS
    pires
    0.79
     accompanies
    0.77
     arose
    0.68
    fter
    0.66
     comprise
    0.65
     comprises
    0.65
     constitutes
    0.65
    hesda
    0.64
     rocked
    0.63
     violates
    0.63
    Act Density 0.259%

    No Known Activations