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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant events or noteworthy occurrences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the significance or importance of events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oreAnd
    -0.79
    raltar
    -0.77
    etheus
    -0.76
    elve
    -0.75
    tein
    -0.73
     chambers
    -0.73
    asus
    -0.73
    ©¶æ
    -0.72
    ippi
    -0.68
    nan
    -0.67
    POSITIVE LOGITS
    killer
    0.87
    breaker
    0.86
    deals
    0.85
     breaker
    0.77
    ership
    0.76
    killers
    0.73
    atical
    0.69
    enance
    0.69
    ability
    0.68
     deal
    0.68
    Act Density 0.020%

    No Known Activations