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

    Neuronpedia

    INDEX
    Explanations

    terms related to suspensions and being suspended

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.70
    %)$
    -0.67
     /\.
    -0.64
    FromJson
    -0.58
     ২০১
    -0.58
    (',');
    -0.58
    WithTag
    -0.58
    ">#
    -0.56
    >';
    -0.56
    寡
    -0.56
    POSITIVE LOGITS
     suspend
    2.89
     suspension
    2.80
     suspended
    2.74
     Suspension
    2.61
     suspensions
    2.55
     suspending
    2.53
     Suspended
    2.49
    suspended
    2.45
    suspension
    2.36
    Suspension
    2.33
    Act Density 0.092%

    No Known Activations