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

    Neuronpedia

    INDEX
    Explanations

    references to towers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.58
    AntiForgeryToken
    -0.53
    GeneratedMessage
    -0.52
     OMITBAD
    -0.51
    tagHelperRunner
    -0.49
    Chham
    -0.49
    propri
    -0.45
    DataAnnotations
    -0.44
    /*
    -0.43
     linkovi
    -0.43
    POSITIVE LOGITS
     Tower
    1.12
    Tower
    1.11
     tower
    1.06
     TOWER
    1.03
    tower
    0.96
     Valley
    0.91
     Island
    0.90
    Valley
    0.89
     VALLEY
    0.87
    Island
    0.85
    Act Density 0.125%

    No Known Activations