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

    Neuronpedia

    INDEX
    Explanations

    references to future events or steps in progression

    oai_token-act-pair · gpt-3.5-turbo

    references to future events or steps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lees
    -0.78
    bows
    -0.71
    lua
    -0.68
    theless
    -0.66
    hist
    -0.63
    hes
    -0.63
     Cout
    -0.63
     Feldman
    -0.62
     Franch
    -0.62
    lee
    -0.62
    POSITIVE LOGITS
     generation
    1.03
     iteration
    0.98
     decade
    0.93
     installment
    0.93
     millenn
    0.88
     step
    0.88
     generations
    0.88
     occupant
    0.84
     phase
    0.82
     incarnation
    0.81
    Act Density 0.039%

    No Known Activations