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

    Neuronpedia

    INDEX
    Explanations

    names of companies and scientific institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pò
    -0.90
     didalam
    -0.89
    luß
    -0.86
     diatas
    -0.85
     perchè
    -0.81
    …..
    -0.77
     eachother
    -0.74
     poichè
    -0.74
     diantaranya
    -0.73
     &
    -0.71
    POSITIVE LOGITS
    —.
    0.73
     beziehungs
    0.71
    ​—
    0.70
    __':
    0.69
     —,
    0.66
    —,
    0.66
     ?
    0.65
     
    0.64
    stateProvider
    0.63
     —
    0.63
    Act Density 0.838%

    No Known Activations