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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to decision-making processes and the importance of being informed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    заб
    -0.16
    ÌĨ
    -0.15
    kits
    -0.15
    /accounts
    -0.14
    /framework
    -0.14
     плеÑĩ
    -0.14
    ίδα
    -0.14
    ắm
    -0.14
    igkeit
    -0.13
    ç§
    -0.13
    POSITIVE LOGITS
     decisions
    0.91
     decision
    0.89
    decision
    0.74
     Decision
    0.69
    Decision
    0.68
     choices
    0.63
    _decision
    0.54
     choice
    0.50
    choices
    0.49
     Choices
    0.49
    Act Density 0.200%

    No Known Activations