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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the action of injecting or influencing something into a system or conversation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥİ
    -0.79
    ģ«
    -0.76
    edom
    -0.76
    main
    -0.67
     Correspond
    -0.67
    fman
    -0.66
    Uncommon
    -0.63
    rant
    -0.63
    ARB
    -0.60
     Codex
    -0.60
    POSITIVE LOGITS
     into
    1.56
     INTO
    1.43
     Into
    1.31
    into
    1.30
     onto
    1.19
     overboard
    0.76
     forth
    0.73
    tion
    0.72
    rafted
    0.70
     wedge
    0.68
    Act Density 0.296%

    No Known Activations