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

    Neuronpedia

    INDEX
    Explanations

    patterns of nested structures or brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     conclud
    -0.79
     eaves
    -0.76
     recre
    -0.73
     corrid
    -0.71
     recon
    -0.70
     reeling
    -0.70
     antioxid
    -0.69
     installations
    -0.68
     fundra
    -0.68
     counselling
    -0.67
    POSITIVE LOGITS
    },
    0.92
    Static
    0.92
    mosp
    0.90
     Pwr
    0.89
    }{
    0.87
    flush
    0.84
    names
    0.84
    });
    0.84
    img
    0.84
    unknown
    0.83
    Act Density 0.005%

    No Known Activations