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

    Neuronpedia

    INDEX
    Explanations

    terms related to high-speed travel and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rung
    -0.15
    ridge
    -0.15
     stair
    -0.14
    umu
    -0.14
     postpon
    -0.13
    fg
    -0.13
    chio
    -0.13
     Slate
    -0.13
    天
    -0.13
    FG
    -0.13
    POSITIVE LOGITS
     speed
    0.73
    speed
    0.65
     speeds
    0.65
     Speed
    0.62
    -speed
    0.61
    Speed
    0.60
    _speed
    0.58
    éĢŁåº¦
    0.55
    .speed
    0.55
     SPEED
    0.55
    Act Density 0.150%

    No Known Activations