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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "hack" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stateProvider
    -0.91
    SourceChecksum
    -0.83
     unknownFields
    -0.80
    AccessorTable
    -0.76
     tartalomajánló
    -0.74
    SharedDtor
    -0.70
     defaultstate
    -0.69
    SharedCtor
    -0.69
    verwijspagina
    -0.69
    UnknownFields
    -0.68
    POSITIVE LOGITS
    ena
    0.99
     hack
    0.88
     hacks
    0.86
    hack
    0.80
    ner
    0.78
     Hack
    0.78
    hu
    0.74
    ona
    0.73
    Hack
    0.72
     HACK
    0.68
    Act Density 0.091%

    No Known Activations