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

    Neuronpedia

    INDEX
    Explanations

    references to directives in programming contexts

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

    directive of dashboard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ​​
    -0.47
    Almost
    -0.45
    tvguidetime
    -0.45
    OrNull
    -0.45
    married
    -0.43
    Nearly
    -0.43
    Marry
    -0.42
    Hang
    -0.40
    money
    -0.40
    smb
    -0.40
    POSITIVE LOGITS
     directive
    2.20
     Directive
    2.09
     directives
    2.03
     Directives
    1.86
    Directive
    1.66
    directive
    1.66
    directives
    1.56
     directiva
    1.19
    Dire
    0.98
    指令
    0.97
    Act Density 0.003%

    No Known Activations