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

    Neuronpedia

    INDEX
    Explanations

    instances of suspension in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of suspension or expulsion in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swick
    -0.80
    zig
    -0.75
    ebus
    -0.73
    ipped
    -0.70
    ãĥ¼ãĤ¯
    -0.70
    estine
    -0.68
    illard
    -0.68
    ocene
    -0.67
    rics
    -0.67
    姫
    -0.66
    POSITIVE LOGITS
     indefinitely
    1.13
     disbelief
    1.05
     suspensions
    0.97
     suspension
    0.92
     suspending
    0.92
     sentences
    0.84
     pending
    0.84
     suspended
    0.83
    ishment
    0.80
    icious
    0.79
    Act Density 0.034%

    No Known Activations