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

    Neuronpedia

    INDEX
    Explanations

    phrases related to disciplinary actions, especially suspensions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "suspended" and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rics
    -0.78
    ebus
    -0.72
     originals
    -0.72
    åĮ
    -0.71
    zig
    -0.68
    fter
    -0.68
    bold
    -0.66
    illard
    -0.66
    swick
    -0.66
    sonian
    -0.65
    POSITIVE LOGITS
     disbelief
    1.03
     suspending
    1.02
     suspended
    1.00
     suspension
    0.99
     suspensions
    0.98
     indefinitely
    0.97
     suspend
    0.91
    ishment
    0.82
     susp
    0.75
    susp
    0.74
    Act Density 0.023%

    No Known Activations