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

    Neuronpedia

    INDEX
    Explanations

    phrases related to involvement in various activities or discussions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate entering or engaging with a topic or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĤ¬
    -0.60
     vanquished
    -0.60
     testament
    -0.59
     condemns
    -0.58
     reconc
    -0.57
    erence
    -0.57
     locals
    -0.57
    ian
    -0.56
     deceased
    -0.56
     alike
    -0.56
    POSITIVE LOGITS
     trouble
    0.97
    itialized
    0.94
    ked
    0.76
    jected
    0.76
     bed
    0.75
     grips
    0.74
     mischief
    0.72
    offensive
    0.71
     contention
    0.70
    clusion
    0.70
    Act Density 0.040%

    No Known Activations