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

    Neuronpedia

    INDEX
    Explanations

    phrases related to experimentation and trying new things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.81
    )];
    -0.66
     يتيمه
    -0.66
    celes
    -0.65
     BoxDecoration
    -0.63
    complexType
    -0.63
    basicConfig
    -0.62
    tableFuture
    -0.62
    WebElementEntity
    -0.61
    íncia
    -0.61
    POSITIVE LOGITS
     trial
    1.41
     Trial
    1.24
     trials
    1.24
    trial
    1.24
     tried
    1.23
    Trial
    1.23
     Try
    1.22
    tried
    1.21
    Tried
    1.20
    試
    1.18
    Act Density 0.182%

    No Known Activations