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

    Neuronpedia

    INDEX
    Explanations

    words related to body parts or physical characteristics

    oai_token-act-pair · gpt-3.5-turbo

    specific sound or phonetic patterns in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -0.82
     ourselves
    -0.76
     oneself
    -0.72
     Vend
    -0.68
     Turks
    -0.68
     Rohing
    -0.68
     Topic
    -0.66
     Mahm
    -0.66
     themselves
    -0.66
     Aval
    -0.65
    POSITIVE LOGITS
    favorite
    1.17
    own
    0.98
    earned
    0.98
     selves
    0.98
     counterparts
    0.97
    iasm
    0.96
    ometown
    0.95
    friends
    0.95
     instincts
    0.95
    cles
    0.94
    Act Density 0.411%

    No Known Activations