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

    Neuronpedia

    INDEX
    Explanations

    sentences that discuss plans, expectations, or current situations

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

    the future

    np_acts-logits-general · gemini-2.0-flash

    planning and future events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     non
    -0.41
     manner
    -0.39
    cdata
    -0.37
     manners
    -0.36
    gzip
    -0.35
     integrated
    -0.35
    vri
    -0.35
     examples
    -0.35
    ure
    -0.35
     muscle
    -0.35
    POSITIVE LOGITS
    unnitel
    0.64
     typelib
    0.57
    tomorrow
    0.57
     prochains
    0.56
     آینده
    0.56
     rencana
    0.56
    future
    0.55
     '\\;'
    0.55
     avenir
    0.54
    FUTURE
    0.53
    Act Density 0.350%

    No Known Activations