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

    Neuronpedia

    INDEX
    Explanations

    the word "Verizon" or variants of it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Ver" and its variations, indicating a focus on specific brands or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ogre
    -0.79
     MP
    -0.72
     shock
    -0.71
     Maple
    -0.68
     LB
    -0.67
     cocktails
    -0.66
     barr
    -0.65
     Ottoman
    -0.64
     starvation
    -0.63
     peanut
    -0.63
    POSITIVE LOGITS
    Ver
    4.17
     Ver
    1.57
    Vers
    1.45
    ver
    1.42
     VER
    1.34
    VER
    1.22
    verse
    1.19
    Wire
    1.15
     ver
    1.14
    verb
    1.13
    Act Density 0.014%

    No Known Activations