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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating movement or transition

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

    Followed by "from there" or similar phrases

    np_acts-logits-general · gemini-2.0-flash

    from there

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     score
    -0.93
     scores
    -0.75
     Score
    -0.73
    score
    -0.66
    Score
    -0.64
     SCORE
    -0.59
     Scores
    -0.57
     scored
    -0.57
    SCORE
    -0.54
    migrationBuilder
    -0.53
    POSITIVE LOGITS
     thereafter
    1.22
    OGND
    1.15
    そこから
    1.10
     therefrom
    1.05
     Thereafter
    1.05
     thence
    0.92
     thereupon
    0.87
     далее
    0.84
     thereon
    0.83
     дальше
    0.83
    Act Density 0.136%

    No Known Activations