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

    Neuronpedia

    INDEX
    Explanations

    verbs related to reasoning and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.59
    zzleHttp
    -0.53
     ویکی‌پدی
    -0.42
    ]}>
    -0.42
    tschaft
    -0.42
    zack
    -0.41
    "])){
    -0.41
    TRIBUN
    -0.40
    atrici
    -0.40
    🔕
    -0.40
    POSITIVE LOGITS
     Considering
    0.49
     Speaking
    0.49
     Looking
    0.48
    Continuing
    0.47
    Speaking
    0.47
     Continuing
    0.46
    Considering
    0.45
    Looking
    0.43
    Talking
    0.43
     Thinking
    0.42
    Act Density 0.571%

    No Known Activations