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

    Neuronpedia

    INDEX
    Explanations

    phrases describing indirect relationships or complex interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    νω
    -0.51
    litian
    -0.47
     Tomé
    -0.46
    PhysRev
    -0.45
    φα
    -0.44
     exactement
    -0.43
     cervix
    -0.42
    estroyer
    -0.42
    romolecules
    -0.41
     greeted
    -0.41
    POSITIVE LOGITS
     indirect
    1.02
     Indirect
    0.97
     indirectly
    0.97
    indirect
    0.92
    Indirect
    0.90
     indirec
    0.86
    AnimationsModule
    0.85
    principalColumn
    0.82
    argout
    0.82
     collateral
    0.80
    Act Density 0.689%

    No Known Activations