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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the actions of simulating gems

    oai_token-act-pair · gpt-3.5-turbo

    opening parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sis
    -0.80
    Hol
    -0.75
    ac
    -0.73
    inn
    -0.72
    oys
    -0.70
    ican
    -0.70
    oot
    -0.70
    isen
    -0.68
    ophobia
    -0.67
    ador
    -0.67
    POSITIVE LOGITS
     uncond
    0.88
    clud
    0.70
     locals
    0.69
     Palestin
    0.68
     oun
    0.68
    enhagen
    0.67
     sidew
    0.67
     neighb
    0.66
    abouts
    0.65
     crossings
    0.65
    Act Density 0.000%

    No Known Activations