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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal actions or investigations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions or concepts related to bringing something to attention or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wine
    -0.70
    rand
    -0.69
     WATCHED
    -0.67
     facult
    -0.66
    lly
    -0.64
    ollen
    -0.63
    VPN
    -0.60
    vich
    -0.58
    TION
    -0.58
    few
    -0.58
    POSITIVE LOGITS
     fruition
    1.29
     bear
    1.09
     heel
    1.06
     prominence
    0.88
     attention
    0.79
     forefront
    0.79
     haunt
    0.73
     boil
    0.72
     maturity
    0.72
     life
    0.72
    Act Density 0.091%

    No Known Activations