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

    Neuronpedia

    INDEX
    Explanations

    instances of suspension or being suspended

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "suspended."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rics
    -0.86
    PT
    -0.83
    ortment
    -0.79
    bold
    -0.76
    ipped
    -0.76
    icians
    -0.73
    ellery
    -0.72
    sis
    -0.71
     Generations
    -0.71
    opher
    -0.71
    POSITIVE LOGITS
     suspended
    1.23
     suspending
    1.22
     suspend
    1.05
     suspension
    1.00
     suspensions
    0.98
     indefinitely
    0.94
     disbelief
    0.90
     susp
    0.89
     handc
    0.78
     lockdown
    0.77
    Act Density 0.017%

    No Known Activations