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

    Neuronpedia

    INDEX
    Explanations

    references to dismissal or termination from a job

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.52
     BrowserModule
    -0.41
    modelBuilder
    -0.40
     препратки
    -0.40
    RTLI
    -0.40
    PerformLayout
    -0.38
     degrés
    -0.37
     utafitiHapana
    -0.37
    __":
    -0.37
    bootstrapcdn
    -0.36
    POSITIVE LOGITS
     fired
    1.09
    fired
    0.96
     Fired
    0.93
    Fired
    0.91
     Known
    0.82
    Known
    0.82
     known
    0.77
    known
    0.75
     launched
    0.71
     KNOWN
    0.70
    Act Density 0.135%

    No Known Activations