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

    Neuronpedia

    INDEX
    Explanations

    links or buttons to click on, typically associated with taking action or navigating through content

    oai_token-act-pair · gpt-3.5-turbo

    phrases focusing on clicking links or buttons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.85
    utenberg
    -0.78
    ELF
    -0.70
    ŀ
    -0.70
    ©¶æ¥µ
    -0.70
    zona
    -0.68
    rament
    -0.66
    ARB
    -0.65
    arnaev
    -0.64
    SourceFile
    -0.64
    POSITIVE LOGITS
     behalf
    1.07
    shore
    0.85
     cue
    0.83
     autop
    0.76
    itiveness
    0.75
    coming
    0.72
    oice
    0.70
    auts
    0.69
    erous
    0.69
     impulse
    0.69
    Act Density 0.038%

    No Known Activations