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

    Neuronpedia

    INDEX
    Explanations

    issues related to problem-solving or challenges faced in completing tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "to" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    figure out how to get

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -0.85
     poffe
    -0.80
     myſelf
    -0.77
    webElementXpaths
    -0.76
     prêtres
    -0.74
     houſe
    -0.74
     ſever
    -0.72
    ſelf
    -0.72
     rê
    -0.72
     pleaſure
    -0.71
    POSITIVE LOGITS
     figure
    0.76
     figured
    0.69
    figure
    0.66
     kind
    0.61
     fine
    0.59
     figuring
    0.54
     get
    0.54
    figured
    0.53
     tweak
    0.52
     tweaked
    0.52
    Act Density 0.251%

    No Known Activations