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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or possibilities regarding outcomes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ########.
    -0.78
     {?}
    -0.71
     Antara
    -0.66
     generally
    -0.63
     Kuru
    -0.63
     prob
    -0.62
    ipto
    -0.61
     inevitable
    -0.61
     usually
    -0.60
     probable
    -0.60
    POSITIVE LOGITS
    ParallelGroup
    0.57
    μαστε
    0.52
    Kariera
    0.52
     fırs
    0.52
     sociaux
    0.51
     vectorielles
    0.50
    penup
    0.50
     chiesto
    0.49
     manutenzione
    0.48
    DataMember
    0.47
    Act Density 0.063%

    No Known Activations