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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events or projects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organized events or programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ecause
    -0.56
    mercial
    -0.52
    ourke
    -0.51
    olia
    -0.50
     srf
    -0.49
    riched
    -0.49
    aiden
    -0.49
    Ô
    -0.49
    ĺħ
    -0.49
    poons
    -0.49
    POSITIVE LOGITS
    iest
    0.82
     itself
    0.68
     portion
    0.62
    liest
    0.62
    osphere
    0.61
    ieth
    0.59
    's
    0.58
    sth
    0.51
     phase
    0.51
     sphere
    0.50
    Act Density 0.907%

    No Known Activations