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

    Neuronpedia

    INDEX
    Explanations

    comparisons of quantities or levels between different subjects

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and expressions of personal experience or participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UTC
    -0.62
     Firm
    -0.59
    itiz
    -0.58
    raltar
    -0.57
    CHAT
    -0.57
     limbo
    -0.55
     MLA
    -0.54
     Knock
    -0.54
    urst
    -0.53
    details
    -0.53
    POSITIVE LOGITS
     barg
    1.13
     ever
    0.83
     realizes
    0.81
    ":[
    0.78
     realize
    0.78
     otherwise
    0.76
    ught
    0.74
    actual
    0.73
     realise
    0.73
     realized
    0.70
    Act Density 0.108%

    No Known Activations