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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "was" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused68>
    -1.24
    <unused43>
    -1.24
    <unused28>
    -1.24
    <unused41>
    -1.24
    <unused3>
    -1.24
    [@BOS@]
    -1.24
    <unused8>
    -1.24
    <unused14>
    -1.24
    <unused74>
    -1.24
    <unused79>
    -1.24
    POSITIVE LOGITS
     was
    1.05
     Was
    0.95
     standard
    0.81
    Was
    0.79
    ,
    0.77
    was
    0.73
     
    0.73
    default
    0.73
     Standard
    0.73
    Default
    0.72
    Act Density 0.804%

    No Known Activations