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

    Neuronpedia

    INDEX
    Explanations

    instances of a specific symbol or character pattern

    oai_token-act-pair · gpt-3.5-turbo

    the specific character string "âĢĶ."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieth
    -0.74
    worms
    -0.71
    ruck
    -0.68
    enei
    -0.64
    iard
    -0.64
    perate
    -0.64
    mop
    -0.64
    icable
    -0.63
    pex
    -0.63
    ides
    -0.63
    POSITIVE LOGITS
    ————————
    1.80
    ————
    1.74
    ————————————————
    1.16
    ——
    0.86
    _-
    0.85
     namely
    0.83
     albeit
    0.83
    especially
    0.76
    whether
    0.72
    albeit
    0.71
    Act Density 0.119%

    No Known Activations