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

    Neuronpedia

    INDEX
    Explanations

    symbols related to directional indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oredCriteria
    -0.62
    ?
    -0.62
     Betracht
    -0.61
    --"
    -0.60
     ddelweddau
    -0.59
    tanleria
    -0.59
     iſt
    -0.58
     itſelf
    -0.58
    RTEE
    -0.57
    gridColumn
    -0.56
    POSITIVE LOGITS
     ↑
    4.09
    ↑
    1.76
    ↑↑
    1.36
    ↑↑↑
    1.16
     ↓
    1.08
    ↓
    1.04
    ↓↓
    0.85
    uparrow
    0.81
    ⤴
    0.77
     [*]
    0.74
    Act Density 0.030%

    No Known Activations