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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "hack" and related terms

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

    hack, hackneyed, hacking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ++++++++++++++++
    -0.41
                  
    -0.41
    ***************
    -0.41
     Coleman
    -0.40
     SRP
    -0.39
    ZT
    -0.39
                                 
    -0.39
     Germain
    -0.38
     Stearns
    -0.38
     Tomlinson
    -0.37
    POSITIVE LOGITS
     hack
    2.31
     Hack
    2.23
    Hack
    2.16
    hack
    2.05
     HACK
    2.00
     hacks
    1.92
     Hacks
    1.72
    hacks
    1.71
     hacked
    1.66
     hacking
    1.62
    Act Density 0.003%

    No Known Activations