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

    Neuronpedia

    INDEX
    Explanations

    references to hacking and dark themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.39
     aang
    -0.35
     operating
    -0.35
    íncia
    -0.32
    The
    -0.32
     jadx
    -0.31
     findes
    -0.31
     emerging
    -0.30
     prévention
    -0.30
    πάρχ
    -0.30
    POSITIVE LOGITS
     hack
    0.78
    fromnode
    0.75
    RuleContext
    0.69
    InjectMocks
    0.68
     poem
    0.68
     pad
    0.67
    endphp
    0.66
     dark
    0.65
     mock
    0.65
     tagline
    0.65
    Act Density 0.181%

    No Known Activations