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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal experiences or encounters

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

    preceding "across," "into," or "on"

    np_acts-logits-general · gemini-2.0-flash

    coming across or stumbling upon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.82
    ]='\
    -0.72
    zzleHttp
    -0.70
     kasarigan
    -0.69
     unknownFields
    -0.68
    __':
    -0.66
    __":
    -0.63
    abetes
    -0.62
    ształ
    -0.62
    PhysRevD
    -0.60
    POSITIVE LOGITS
     encounter
    1.69
     encountered
    1.56
    encounter
    1.55
     Encounter
    1.53
     encounters
    1.52
     encountering
    1.45
    Encounter
    1.40
     stumble
    1.30
     stumbled
    1.28
     rencontre
    1.11
    Act Density 0.264%

    No Known Activations