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

    Neuronpedia

    INDEX
    Explanations

    negative evaluations or downfalls related to experiences or circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anmoins
    -0.82
    GOTREF
    -0.75
    rijke
    -0.70
    jsonwebtoken
    -0.68
    PhysRevLett
    -0.65
    Marilyn
    -0.64
     stationnement
    -0.62
     Drapeau
    -0.61
     plenamente
    -0.61
    SerializeField
    -0.60
    POSITIVE LOGITS
     worst
    2.23
     worse
    2.14
     Worst
    2.02
    worst
    2.00
    Worse
    1.98
    worse
    1.92
    Worst
    1.92
     Worse
    1.89
     bad
    1.57
     peor
    1.51
    Act Density 0.126%

    No Known Activations