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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'Angel' with a strong focus on specificity

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Angel" and related entities or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rences
    -0.80
    llah
    -0.74
    yip
    -0.70
     elig
    -0.68
     independents
    -0.67
    cloth
    -0.66
    olicy
    -0.65
    ãģ¦
    -0.65
    merce
    -0.64
    theless
    -0.64
    POSITIVE LOGITS
    enos
    1.38
    eno
    1.19
    ique
    1.06
    ina
    1.00
    ica
    0.97
    icals
    0.96
    inian
    0.94
    ient
    0.92
    ista
    0.92
    ic
    0.92
    Act Density 0.030%

    No Known Activations