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

    Neuronpedia

    INDEX
    Explanations

    words that represent the letters or parts of letters and compositions in written language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     haer
    -0.59
     herv
    -0.58
     bere
    -0.57
     kere
    -0.57
     թվ
    -0.56
     Martinez
    -0.54
     dice
    -0.54
     consulter
    -0.54
    atzen
    -0.53
    chere
    -0.53
    POSITIVE LOGITS
    ThroughAttribute
    0.91
    tagext
    0.89
    SizeF
    0.82
    djangoproject
    0.73
    unknownFields
    0.72
    PYX
    0.71
    CloseOperation
    0.71
    hoeddwyd
    0.70
     '',
    0.69
     ]
    0.69
    Act Density 0.181%

    No Known Activations