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

    Neuronpedia

    INDEX
    Explanations

    references to specific characters or actions occurring in a narrative context

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

    Unusual situations or observations

    np_acts-logits-general · gemini-2.0-flash

    saw defendant or pile of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    apunov
    -0.52
    szak
    -0.50
     impuesto
    -0.47
    icoli
    -0.46
     vált
    -0.46
    irchen
    -0.45
     impuestos
    -0.44
     gynhyrchwyd
    -0.43
    ổi
    -0.43
    心中的
    -0.43
    POSITIVE LOGITS
     seemed
    0.74
     something
    0.66
    Someone
    0.66
     someone
    0.66
     Looked
    0.65
    +#+
    0.64
     Someone
    0.64
     похоже
    0.64
     strangely
    0.63
     suddenly
    0.62
    Act Density 0.207%

    No Known Activations