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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sending messages or signals to different groups or individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve sending messages or signals to various audiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abases
    -0.72
    lux
    -0.69
     rack
    -0.69
    ources
    -0.69
     Burk
    -0.65
    ossier
    -0.65
    ourced
    -0.65
    addons
    -0.64
     Brune
    -0.63
    riages
    -0.61
    POSITIVE LOGITS
     message
    0.80
    arers
    0.75
    message
    0.74
     messages
    0.74
     behav
    0.72
    wcs
    0.69
     caution
    0.69
     beware
    0.67
     Messages
    0.66
     deterrence
    0.66
    Act Density 0.255%

    No Known Activations