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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "hip" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /**
    -0.47
    ----</
    -0.44
    <bos>
    -0.40
    écart
    -0.36
     appreciation
    -0.36
     Czechoslovak
    -0.35
     OnTrigger
    -0.35
     casualty
    -0.34
     Celebration
    -0.34
     conveyor
    -0.34
    POSITIVE LOGITS
    bitField
    0.66
    hip
    0.66
     CreateTagHelper
    0.59
    ice
    0.57
    ParseTree
    0.56
    蚪
    0.54
     Cow
    0.54
    pyx
    0.52
     Bark
    0.51
     hitch
    0.50
    Act Density 0.472%

    No Known Activations