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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making an impact or creating change

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of making a positive impact or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quotation
    -0.79
    ©¶æ
    -0.75
     contracted
    -0.71
     faults
    -0.69
     crab
    -0.67
     quotations
    -0.67
     diction
    -0.64
     plagiar
    -0.63
    gress
    -0.62
     Sche
    -0.61
    POSITIVE LOGITS
    elight
    0.76
    hole
    0.75
    inel
    0.72
    eful
    0.70
     GOODMAN
    0.65
    arios
    0.65
     materially
    0.65
    holes
    0.64
    :{
    0.64
    ersive
    0.64
    Act Density 0.040%

    No Known Activations