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

    Neuronpedia

    INDEX
    Explanations

    connections between causation and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.54
    <eos>
    -0.54
     $
    -0.51
    ;
    -0.49
     
    -0.48
     All
    -0.47
    :
    -0.46
     &
    -0.46
    <bos>
    -0.46
     “
    -0.46
    POSITIVE LOGITS
    \{\\
    0.96
    SequentialGroup
    0.94
    ledem
    0.90
    KommentareTeilen
    0.88
     BoxFit
    0.85
    AddTagHelper
    0.83
    tagext
    0.82
    ApiModelProperty
    0.81
     ―――――
    0.79
    styleType
    0.78
    Act Density 2.061%

    No Known Activations