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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conveying a message or communication

    oai_token-act-pair · gpt-3.5-turbo

    references to communication or conveying messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ternity
    -0.74
    ords
    -0.71
    itates
    -0.71
    vez
    -0.70
    endars
    -0.69
    entimes
    -0.69
    igs
    -0.68
    ced
    -0.68
    fac
    -0.67
    everal
    -0.67
    POSITIVE LOGITS
     message
    1.07
     conveyed
    1.04
     messages
    0.91
     loud
    0.88
     communicated
    0.81
    message
    0.80
     relayed
    0.80
     preached
    0.79
    mith
    0.76
     reson
    0.76
    Act Density 0.058%

    No Known Activations