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

    Neuronpedia

    INDEX
    Explanations

    statements related to personal struggles and mental health issues

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

    Character names

    np_acts-logits-general · gemini-2.0-flash

    character names followed by actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.76
     Wicidata
    -0.70
     meines
    -0.66
     mojej
    -0.64
     mijn
    -0.63
     moim
    -0.62
     my
    -0.60
     meiner
    -0.59
    tagHelperRunner
    -0.59
    AccessorTable
    -0.58
    POSITIVE LOGITS
     blackmail
    0.88
     overheard
    0.85
     flashback
    0.83
     threatens
    0.77
     disguised
    0.77
     flashbacks
    0.77
     reveals
    0.77
     revealed
    0.74
     angrily
    0.73
     accidentally
    0.72
    Act Density 0.433%

    No Known Activations