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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating close association or partnership between entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "alongside" indicating relationships or associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asse
    -0.82
    jab
    -0.76
    ggle
    -0.73
    ortex
    -0.72
    ck
    -0.72
    ̶
    -0.70
    chin
    -0.69
    ek
    -0.68
    nexus
    -0.68
    press
    -0.67
    POSITIVE LOGITS
     others
    0.76
    lihood
    0.73
     hers
    0.72
     fellow
    0.70
     Sakuya
    0.69
     colleagues
    0.68
     him
    0.67
     ours
    0.66
     theirs
    0.64
     other
    0.64
    Act Density 0.041%

    No Known Activations