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

    Neuronpedia

    INDEX
    Explanations

    keywords or phrases related to corresponding or communicating with others

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "correspond."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uv
    -0.74
    GPU
    -0.70
     Scotia
    -0.67
    oult
    -0.66
    STD
    -0.65
     Bedford
    -0.65
    foot
    -0.64
    Downloadha
    -0.62
    HUD
    -0.62
    STRUCT
    -0.60
    POSITIVE LOGITS
    ingly
    1.14
     correspond
    1.01
    ences
    1.01
     Correspond
    0.98
    abilia
    0.91
    encies
    0.91
    acters
    0.86
    ents
    0.83
     newsp
    0.80
    ificantly
    0.80
    Act Density 0.007%

    No Known Activations