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

    Neuronpedia

    INDEX
    Explanations

    references to coordinates and failures in processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sand
    -0.73
    grove
    -0.63
    OIR
    -0.63
    pty
    -0.62
    IntoConstraints
    -0.61
     MainAxisSize
    -0.60
    ところ
    -0.60
    Sand
    -0.60
     sand
    -0.59
     Holtz
    -0.57
    POSITIVE LOGITS
    fail
    1.05
     Fail
    0.99
     fail
    0.95
     Fails
    0.93
    Fail
    0.91
     FAIL
    0.85
    Fails
    0.80
    fails
    0.76
     fails
    0.74
    FAIL
    0.69
    Act Density 0.080%

    No Known Activations