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

    Neuronpedia

    INDEX
    Explanations

    hyphenated words and phrases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    efer
    -0.74
    amines
    -0.74
    irez
    -0.73
    poke
    -0.71
    erest
    -0.70
    elsen
    -0.69
    omas
    -0.68
    enez
    -0.68
    icho
    -0.68
    ptives
    -0.67
    POSITIVE LOGITS
     otherwise
    1.37
    nam
    0.77
     nons
    0.72
    None
    0.71
     none
    0.67
     unrem
    0.65
     nutshell
    0.65
     circumst
    0.65
    animate
    0.64
     casual
    0.63
    Act Density 0.137%

    No Known Activations