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

    Neuronpedia

    INDEX
    Explanations

    phrases introducing specific examples or explanations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce specific examples or clarifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obal
    -0.71
    toggle
    -0.69
    redit
    -0.66
     Kard
    -0.66
    estern
    -0.65
    ige
    -0.65
     Intercept
    -0.61
    animous
    -0.61
    ocene
    -0.61
    orc
    -0.61
    POSITIVE LOGITS
     namely
    0.85
    forward
    0.84
    forth
    0.76
     yours
    0.74
    çĶ°
    0.73
    soever
    0.70
     ours
    0.70
    entimes
    0.65
    butt
    0.64
    ï¸ı
    0.63
    Act Density 0.026%

    No Known Activations