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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal actions and investigations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ongoing investigations or legal actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ľ
    -0.79
    Suddenly
    -0.75
    pron
    -0.75
    Liter
    -0.71
    Born
    -0.70
    å¦
    -0.70
    robe
    -0.67
    weak
    -0.66
    pit
    -0.65
    Marginal
    -0.65
    POSITIVE LOGITS
     intends
    1.21
     vowed
    1.11
     expects
    1.11
     urged
    1.06
     requested
    1.04
     issued
    1.03
     hopes
    1.00
     plans
    0.99
     reiterated
    0.99
     apologised
    0.96
    Act Density 0.229%

    No Known Activations