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

    Neuronpedia

    INDEX
    Explanations

    adjectives indicating strong beliefs or support for a particular cause

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate strong and unwavering support or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.99
    hops
    -0.79
    hazard
    -0.73
    nesota
    -0.71
    ysc
    -0.69
    ovember
    -0.68
    adish
    -0.68
    ammers
    -0.66
     Takeru
    -0.65
    pta
    -0.65
    POSITIVE LOGITS
    ly
    0.95
     supporter
    0.81
    itive
    0.81
    ELY
    0.77
     adherent
    0.75
    è¦
    0.71
     loyal
    0.71
     pacif
    0.70
    ãĥ¼ãĤ¯
    0.70
     proponent
    0.70
    Act Density 0.021%

    No Known Activations