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

    Neuronpedia

    INDEX
    Explanations

    terms related to clips and bindings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnknownFieldSet
    -0.89
    NegativeButton
    -0.87
    AndEndTag
    -0.85
    enumii
    -0.83
    antMatchers
    -0.82
    openConnection
    -0.81
    EndInit
    -0.80
    HostException
    -0.79
     NDL
    -0.78
    --}}
    -0.77
    POSITIVE LOGITS
     clip
    2.33
     clips
    2.15
     Clip
    2.11
     Clips
    2.03
    Clip
    1.98
    clip
    1.96
    Clips
    1.78
    clips
    1.78
     clipped
    1.65
     CLIP
    1.62
    Act Density 0.080%

    No Known Activations