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

    Neuronpedia

    INDEX
    Explanations

    concepts related to personal and professional choices and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.73
    ChildScrollView
    -0.72
    Portail
    -0.72
     himſelf
    -0.69
     câte
    -0.67
     Majefty
    -0.67
    InjectAttribute
    -0.66
     myſelf
    -0.66
    SuppressLint
    -0.63
     bisexual
    -0.62
    POSITIVE LOGITS
     choices
    0.69
     choice
    0.58
     influence
    0.55
     shape
    0.53
    choices
    0.51
     Choices
    0.50
     influences
    0.50
     choose
    0.48
     choix
    0.48
    Choices
    0.48
    Act Density 0.382%

    No Known Activations