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

    Neuronpedia

    INDEX
    Explanations

    phrases related to large quantities or overwhelming situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe overwhelming or excessive amounts related to negative situations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    paces
    -0.78
    acus
    -0.78
    ours
    -0.77
    few
    -0.72
    jad
    -0.71
    orp
    -0.71
    ħĭ
    -0.71
    mate
    -0.70
    vale
    -0.68
    keeper
    -0.68
    POSITIVE LOGITS
     negativity
    1.10
     misinformation
    1.00
     criticism
    0.92
     discontent
    0.91
     publicity
    0.89
     acron
    0.89
     cancell
    0.88
     arrivals
    0.87
     paperwork
    0.87
     negative
    0.86
    Act Density 0.159%

    No Known Activations