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

    Neuronpedia

    INDEX
    Explanations

    words related to affection or preference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.94
     ſtate
    -0.91
     pleaſure
    -0.91
     houſe
    -0.88
     raiſ
    -0.86
     Jefus
    -0.85
     neceff
    -0.83
     himſelf
    -0.83
     itſelf
    -0.82
     poffible
    -0.82
    POSITIVE LOGITS
    __((
    0.52
    ————————————
    0.45
    ########.
    0.44
     gainera
    0.43
    ]){
    0.43
     AssemblyTitle
    0.43
     createContext
    0.42
    ագրություններ
    0.42
    а
    0.41
    ือก
    0.41
    Act Density 0.049%

    No Known Activations