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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives describing things or actions

    oai_token-act-pair · gpt-3.5-turbo

    positive and favorable descriptions of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    insula
    -0.62
    ivities
    -0.61
     alcoholism
    -0.58
    odan
    -0.58
    oggle
    -0.57
    guyen
    -0.57
    ership
    -0.56
    etus
    -0.56
    ruction
    -0.55
    elist
    -0.55
    POSITIVE LOGITS
     enough
    0.89
     compared
    0.76
     considering
    0.74
     anyway
    0.74
    ISH
    0.73
     aest
    0.72
    enough
    0.72
    ly
    0.71
    bones
    0.69
    ingly
    0.68
    Act Density 0.124%

    No Known Activations