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

    Neuronpedia

    INDEX
    Explanations

    verbs in the process of changing or transitioning

    oai_token-act-pair · gpt-3.5-turbo

    terms related to vegetarianism or dietary choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.73
    hare
    -0.72
    channelAvailability
    -0.71
    manship
    -0.71
    INESS
    -0.69
     Institution
    -0.66
    姫
    -0.66
    ONES
    -0.65
    frames
    -0.65
     Cosponsors
    -0.65
    POSITIVE LOGITS
    ices
    1.01
    ggie
    1.00
    xt
    0.85
    lez
    0.82
    leted
    0.81
     ve
    0.80
    mber
    0.80
    zx
    0.79
    thereum
    0.78
    gging
    0.77
    Act Density 0.006%

    No Known Activations