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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a transition in topic or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize transitions or shifts in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iege
    -0.76
    oen
    -0.71
     teasp
    -0.71
    æ©
    -0.68
    igmatic
    -0.66
    onica
    -0.66
    rue
    -0.63
    ;;;;
    -0.62
    Null
    -0.62
    eal
    -0.62
    POSITIVE LOGITS
     we
    1.00
    rely
    0.80
     they
    0.77
     you
    0.75
     he
    0.70
    's
    0.68
    has
    0.67
     everyone
    0.65
     seems
    0.65
     it
    0.64
    Act Density 0.077%

    No Known Activations