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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that."

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

    "That" followed by a personal pronoun or auxiliary verb

    np_acts-logits-general · gemini-2.0-flash

    I think that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.49
     gyhoeddwyd
    -0.42
     (!_
    -0.42
    ²/
    -0.39
    piram
    -0.39
    ArrowToggle
    -0.39
    errHandler
    -0.39
     Wiktionnaire
    -0.38
    hasMany
    -0.38
    windowFixed
    -0.37
    POSITIVE LOGITS
     autorytatywna
    0.53
    SourceChecksum
    0.53
     linkovi
    0.50
    ècie
    0.41
     they
    0.41
     we
    0.41
    戬
    0.40
     somebody
    0.40
     asymptotically
    0.39
     siquiera
    0.38
    Act Density 0.261%

    No Known Activations