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

    Neuronpedia

    INDEX
    Explanations

    terms related to effects and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olen
    -0.16
    och
    -0.16
     Sob
    -0.15
    беÑĢ
    -0.15
     Woo
    -0.15
    ÙĨÙĩ
    -0.15
     pier
    -0.15
    tem
    -0.15
    ils
    -0.14
     Hir
    -0.14
    POSITIVE LOGITS
    _mE
    0.18
    actionDate
    0.17
    _tF
    0.17
    æŃ©
    0.16
    _mD
    0.16
    _tE
    0.16
     indeb
    0.15
    inalg
    0.15
    edelta
    0.15
    Forge
    0.15
    Act Density 0.020%

    No Known Activations