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

    Neuronpedia

    INDEX
    Explanations

    various subjects of discussion or analysis within a given context

    oai_token-act-pair · gpt-3.5-turbo

    significant topics or elements related to various forms of assessment or evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vich
    -0.66
    livion
    -0.59
     Hayward
    -0.58
     Cancel
    -0.56
     john
    -0.56
     Knot
    -0.56
    verages
    -0.56
     Mayo
    -0.55
     Hague
    -0.55
     Everett
    -0.54
    POSITIVE LOGITS
    mith
    0.82
    hops
    0.81
    hips
    0.80
     gobl
    0.74
    izers
    0.72
     embr
    0.65
     confir
    0.65
     tackled
    0.65
    behind
    0.64
     fielded
    0.64
    Act Density 0.311%

    No Known Activations