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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "from" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.63
    깐
    -0.54
    timeScale
    -0.50
    shadowOpacity
    -0.50
    ɕ
    -0.47
    quake
    -0.46
    amethasone
    -0.45
     rospy
    -0.45
     kadar
    -0.44
    inca
    -0.43
    POSITIVE LOGITS
    FROM
    0.93
     FROM
    0.89
     afar
    0.84
     Từ
    0.80
     whence
    0.80
     From
    0.79
    From
    0.77
    getFrom
    0.77
     perspective
    0.77
    desde
    0.74
    Act Density 0.175%

    No Known Activations