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

    Neuronpedia

    INDEX
    Explanations

    references to human resources (HR) departments and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to human rights organizations and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tin
    -0.88
    tsky
    -0.77
    meric
    -0.76
    cules
    -0.74
    pher
    -0.70
    artney
    -0.70
    arning
    -0.70
    bell
    -0.69
     Albion
    -0.66
     Flavoring
    -0.64
    POSITIVE LOGITS
    istically
    0.88
    ueless
    0.78
    OUGH
    0.78
    isting
    0.76
    ifts
    0.74
    ues
    0.71
    ingly
    0.70
    lasses
    0.69
    isted
    0.68
    ickson
    0.67
    Act Density 0.098%

    No Known Activations