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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and emotional honesty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Presumably
    -0.57
     doubtless
    -0.54
     presumably
    -0.53
    ...>
    -0.52
    nearly
    -0.50
    Szer
    -0.49
     forse
    -0.49
    presumably
    -0.49
    -0.49
     wry
    -0.48
    POSITIVE LOGITS
    🏾
    0.92
     smh
    0.80
     niggas
    0.78
     Normdatei
    0.77
    AlterField
    0.77
     nigga
    0.76
     ain
    0.75
    adaptiveStyles
    0.71
     dope
    0.68
     tryna
    0.68
    Act Density 0.226%

    No Known Activations