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

    Neuronpedia

    INDEX
    Explanations

    references to "long-standing" issues or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scher
    -0.70
     Cube
    -0.70
     Avenger
    -0.69
     crowds
    -0.64
     dstg
    -0.64
     Materials
    -0.63
     powd
    -0.60
     suits
    -0.60
     Coch
    -0.60
     Subst
    -0.60
    POSITIVE LOGITS
     awaited
    0.94
    secret
    0.78
    peat
    0.78
    straight
    0.76
    standing
    0.75
     uninterrupted
    0.71
    awaited
    0.71
    ago
    0.69
    atlantic
    0.69
     straight
    0.68
    Act Density 0.034%

    No Known Activations