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

    Neuronpedia

    INDEX
    Explanations

    situations where events are canceled or suspended

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating reasons for cancellations or closures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Registered
    -0.72
    rawdownloadcloneembedreportprint
    -0.68
    FIG
    -0.68
    Coin
    -0.68
    Led
    -0.66
    jad
    -0.66
    hered
    -0.66
    jet
    -0.65
    VR
    -0.64
    ry
    -0.64
    POSITIVE LOGITS
     disagreements
    0.92
     objections
    0.92
     unforeseen
    0.90
     insufficient
    0.90
     breaching
    0.90
     violating
    0.89
     unspecified
    0.87
     complications
    0.87
     violations
    0.87
     unsatisf
    0.84
    Act Density 0.237%

    No Known Activations