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

    Neuronpedia

    INDEX
    Explanations

    words related to assigning blame or responsibility to someone or something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of a scapegoat

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.87
    luent
    -0.79
    hander
    -0.76
    ocrine
    -0.74
    rique
    -0.74
    nen
    -0.69
    adal
    -0.69
    obbies
    -0.68
    heid
    -0.68
    cyclop
    -0.67
    POSITIVE LOGITS
     scapego
    1.38
    apego
    0.89
    ãĤ©
    0.78
    ãĥķãĤ¡
    0.71
    ateg
    0.69
    âĢķ
    0.68
     burden
    0.68
    wx
    0.66
    selage
    0.65
     blame
    0.65
    Act Density 0.011%

    No Known Activations