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

    Neuronpedia

    INDEX
    Explanations

    words related to love

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Love" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     credential
    -0.86
    epad
    -0.72
    batch
    -0.70
    EA
    -0.69
     deleg
    -0.69
    cially
    -0.67
    chn
    -0.66
    cript
    -0.66
     discretionary
    -0.65
     gran
    -0.65
    POSITIVE LOGITS
     Love
    3.70
    Love
    2.84
     LOVE
    2.55
    love
    2.22
     love
    2.13
     Loving
    2.08
     Hate
    1.62
     Lover
    1.56
     Lovely
    1.49
     loves
    1.36
    Act Density 0.018%

    No Known Activations