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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing gratitude or supportive sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.76
     autorytatywna
    -0.71
     createSprite
    -0.68
    FilterChain
    -0.67
     <<<<<<<<<<<<<<
    -0.66
    writeFieldEnd
    -0.65
    :✨
    -0.64
     étoient
    -0.63
    -0.63
     avoient
    -0.62
    POSITIVE LOGITS
     hereby
    0.75
     thank
    0.68
     implore
    0.67
     request
    0.61
     invite
    0.61
     urge
    0.60
     salute
    0.59
     welcome
    0.57
     commend
    0.55
     applaud
    0.55
    Act Density 0.324%

    No Known Activations