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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical descriptions or instructions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     variés
    -0.53
     Infórmanos
    -0.53
     täv
    -0.53
     [*]
    -0.52
     cérami
    -0.52
    sidemargin
    -0.52
     habet
    -0.50
    StructEnd
    -0.49
    Diz
    -0.48
     allmän
    -0.48
    POSITIVE LOGITS
     "..\..\..\
    0.74
     "..\..\
    0.64
    temon
    0.60
    cokinetics
    0.59
    IVATE
    0.59
    ukone
    0.57
    ICLE
    0.56
    чатки
    0.56
    anyeol
    0.54
     Lagi
    0.54
    Act Density 0.014%

    No Known Activations