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

    Neuronpedia

    INDEX
    Explanations

    concessive clauses that introduce contrasting or contradictory information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Either
    -0.81
    Either
    -0.79
     either
    -0.78
    either
    -0.74
     malah
    -0.69
     invece
    -0.68
     entweder
    -0.67
    tagHelperRunner
    -0.66
    even
    -0.66
     even
    -0.64
    POSITIVE LOGITS
     technically
    1.29
     initially
    1.22
     nominally
    1.19
     ostensibly
    1.08
     admittedly
    1.02
     theoretically
    1.01
     outwardly
    0.98
     inicialmente
    0.97
     superfic
    0.95
     Initially
    0.94
    Act Density 0.673%

    No Known Activations