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

    Neuronpedia

    INDEX
    Explanations

    mentions of friends or feelings of attraction

    oai_token-act-pair · gemini-2.0-flash

    words related to friendships and relationships

    np_token-act-pair-logits · gpt-4o-mini

    friends

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     close
    -1.70
     closer
    -1.65
    close
    -1.48
     Close
    -1.46
    closer
    -1.40
     closest
    -1.39
     Closer
    -1.32
    Close
    -1.32
     CLOSE
    -1.30
    CLOSE
    -1.13
    POSITIVE LOGITS
     فريبيس
    0.71
     photolibrary
    0.66
    ſelves
    0.63
     CreateTagHelper
    0.59
     Мексичка
    0.59
     säll
    0.58
     Pilate
    0.58
     Efq
    0.57
    ároz
    0.57
    ocities
    0.56
    Act Density 0.833%

    No Known Activations