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

    Neuronpedia

    INDEX
    Explanations

    phrases related to providing information or advice

    oai_token-act-pair · gpt-3.5-turbo

    words related to tips and advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FN
    -0.82
     Klux
    -0.81
    hap
    -0.80
    FACE
    -0.68
    flu
    -0.68
     intolerable
    -0.67
     unden
    -0.66
    ikhail
    -0.64
     adolesc
    -0.64
     ILCS
    -0.63
    POSITIVE LOGITS
     advice
    0.78
    iquette
    0.77
     recommendation
    0.72
     Instruct
    0.71
     Helpful
    0.69
     guides
    0.67
     direction
    0.66
     Techniques
    0.65
     rounding
    0.65
     Guid
    0.64
    Act Density 0.302%

    No Known Activations