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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of tuning

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to adjusting or aligning something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anmar
    -0.76
    pha
    -0.73
    perse
    -0.72
    lain
    -0.70
    humans
    -0.68
    Magikarp
    -0.68
    ãĤ¨ãĥ«
    -0.68
    inals
    -0.64
    Ĥİ
    -0.64
    URES
    -0.63
    POSITIVE LOGITS
     tuned
    1.10
     tuning
    1.02
     tune
    0.98
     tun
    0.87
     tunes
    0.87
     Tune
    0.86
     horns
    0.84
     Tun
    0.84
    tun
    0.81
    eness
    0.81
    Act Density 0.028%

    No Known Activations