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

    Neuronpedia

    INDEX
    Explanations

    phrases related to contrasting choices or situations

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases that introduce alternatives or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SHIP
    -0.81
    poke
    -0.80
    erest
    -0.77
    :(
    -0.74
    elsen
    -0.74
    enez
    -0.72
    ilege
    -0.71
    blems
    -0.71
    ATA
    -0.71
    efer
    -0.70
    POSITIVE LOGITS
     otherwise
    0.92
     circumst
    0.79
     decay
    0.73
     wise
    0.66
     powerless
    0.64
     grain
    0.64
     nons
    0.63
    rogens
    0.63
     uncon
    0.63
    animate
    0.63
    Act Density 0.176%

    No Known Activations