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

    Neuronpedia

    INDEX
    Explanations

    phrases with the substring "lf"

    oai_token-act-pair · gpt-3.5-turbo

    references to self-related concepts or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rabbit
    -0.80
     Flags
    -0.78
     Pose
    -0.75
     Powers
    -0.74
    Shot
    -0.73
     CLSID
    -0.71
     CPC
    -0.68
     Virgin
    -0.67
     Decay
    -0.66
     Samoa
    -0.63
    POSITIVE LOGITS
    lf
    1.29
    rint
    1.14
    actory
    1.11
    andom
    1.07
    ibrary
    1.03
    onso
    1.01
    oyd
    0.97
    reet
    0.96
    enn
    0.92
    riger
    0.92
    Act Density 0.006%

    No Known Activations