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

    Neuronpedia

    INDEX
    Explanations

    references to scheduling and job opportunities

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

    Text after hypothetical scenarios starting with "if"

    np_acts-logits-general · gemini-2.0-flash

    Sequencing, transitions, or consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ˮ
    -0.65
     оригіналу
    -0.59
    tonsoft
    -0.58
    '][]
    -0.58
     صوتيه
    -0.58
     Meksiku
    -0.58
     lẫn
    -0.57
    aarrggbb
    -0.56
    ziell
    -0.56
    °;
    -0.55
    POSITIVE LOGITS
     then
    1.16
     thì
    0.96
     entonces
    0.93
     THEN
    0.91
     allora
    0.91
    的话
    0.87
    的話
    0.86
     Then
    0.83
    then
    0.82
     akkor
    0.77
    Act Density 0.385%

    No Known Activations