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

    Neuronpedia

    INDEX
    Explanations

    announcement or statement of positive reception or approval

    oai_token-act-pair · gpt-3.5-turbo

    expressions of positivity or satisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lag
    -0.65
    plane
    -0.63
    VERTISEMENT
    -0.62
    hemy
    -0.61
    ilk
    -0.60
     inferior
    -0.60
     Tsukuyomi
    -0.59
    hang
    -0.57
    anity
    -0.57
    gery
    -0.56
    POSITIVE LOGITS
     announce
    0.72
    leased
    0.69
    fully
    0.68
     delighted
    0.68
     thrilled
    0.68
     pleased
    0.68
    dy
    0.66
     Cosponsors
    0.65
    quartered
    0.64
    ecided
    0.62
    Act Density 0.110%

    No Known Activations