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

    Neuronpedia

    INDEX
    Explanations

    words related to alternatives or variations

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "alternate" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.75
     herd
    -0.75
     living
    -0.68
     speech
    -0.64
     hearing
    -0.63
     dust
    -0.63
     hearts
    -0.62
    flies
    -0.62
     MIL
    -0.61
     fathers
    -0.60
    POSITIVE LOGITS
    atives
    1.27
    ately
    1.21
    acy
    1.20
    atell
    1.18
    ative
    1.17
    ates
    1.16
    acies
    1.13
    atile
    1.12
    ate
    1.10
    atility
    1.08
    Act Density 0.024%

    No Known Activations