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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" and variations of "those."

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

    "that" or "who" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    that come after

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WithEmail
    -0.53
    yelidikan
    -0.53
    Endian
    -0.50
    ual
    -0.50
     mustard
    -0.49
    ódó
    -0.48
     muft
    -0.47
    Eloquent
    -0.46
    Atoi
    -0.46
    Must
    -0.46
    POSITIVE LOGITS
     they
    0.94
     we
    0.93
     mình
    0.91
     you
    0.85
    TagHelper
    0.75
     he
    0.74
     previously
    0.72
     normally
    0.69
     traditionally
    0.67
     otherwise
    0.67
    Act Density 0.230%

    No Known Activations