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

    Neuronpedia

    INDEX
    Explanations

    technical terminology and measurements related to research methodologies and analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ""],
    -0.67
    DIPSETTING
    -0.60
    AsUp
    -0.49
    SourceChecksum
    -0.49
    iblichen
    -0.48
     hort
    -0.44
     uLocal
    -0.44
     bezeichneter
    -0.43
     macro
    -0.42
     '\\;'
    -0.42
    POSITIVE LOGITS
     balení
    0.54
    horabuena
    0.54
     anún
    0.50
     paard
    0.49
    protoimpl
    0.48
     saveiro
    0.48
     salão
    0.47
     enamorado
    0.46
    Aiheesta
    0.45
     trouw
    0.44
    Act Density 0.090%

    No Known Activations