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

    Neuronpedia

    INDEX
    Explanations

    the word "that" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stdc
    -0.74
     hierogly
    -0.73
    NameInMap
    -0.71
     flocc
    -0.67
     feest
    -0.66
     cyc
    -0.65
     fuckin
    -0.65
     talkin
    -0.65
    complexContent
    -0.65
     Viter
    -0.64
    POSITIVE LOGITS
    AlterField
    0.99
     the
    0.87
    "])
    0.80
    assertThat
    0.77
     “
    0.76
     if
    0.73
    getCmp
    0.72
     when
    0.72
    "]);
    0.72
    )";
    0.70
    Act Density 0.456%

    No Known Activations