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

    Neuronpedia

    INDEX
    Explanations

    quantifiable metrics or parameters related to specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reſ
    -0.89
     myſelf
    -0.84
     Theſe
    -0.83
     Efq
    -0.81
     purpoſe
    -0.80
     Eſ
    -0.76
     $_"
    -0.74
     ſtate
    -0.74
     raiſ
    -0.74
     Monfieur
    -0.73
    POSITIVE LOGITS
    Hochspringen
    0.58
    发表于
    0.54
    Portale
    0.54
     transfieras
    0.53
    igshid
    0.49
     متعلقه
    0.45
     muuta
    0.45
     kasarigan
    0.45
     cachorros
    0.45
     agrega
    0.44
    Act Density 0.503%

    No Known Activations