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

    Neuronpedia

    INDEX
    Explanations

    proper names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.96
    issance
    -0.80
     behavi
    -0.75
    thood
    -0.73
    BOOK
    -0.72
    Ø©
    -0.71
    SHIP
    -0.70
    cial
    -0.70
     CTR
    -0.68
    ciation
    -0.68
    POSITIVE LOGITS
    ucky
    1.10
    rell
    0.96
    mare
    0.91
    wood
    0.90
    uck
    0.86
    rust
    0.85
    isl
    0.84
    ridge
    0.83
    anic
    0.82
     Dover
    0.78
    Act Density 0.014%

    No Known Activations