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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transitional phrases indicating relationships between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſtate
    -0.77
     sorption
    -0.76
     cuffs
    -0.73
     RSSSF
    -0.73
     columb
    -0.72
     purpoſe
    -0.72
     Huguen
    -0.72
     Dependence
    -0.70
     Matka
    -0.69
     Yoh
    -0.69
    POSITIVE LOGITS
     being
    1.14
     is
    1.00
     also
    0.98
     be
    0.94
     not
    0.92
     becoming
    0.89
     a
    0.85
     was
    0.83
     être
    0.82
     going
    0.81
    Act Density 0.329%

    No Known Activations