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

    Neuronpedia

    INDEX
    Explanations

    phrases related to familial and relational dynamics, especially concerning support and loss

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ritel
    -0.15
    :async
    -0.15
    deniz
    -0.15
     ruku
    -0.15
    ("")]↵
    -0.14
    .Debugger
    -0.14
    NECT
    -0.14
    optgroup
    -0.14
    edis
    -0.14
    EDI
    -0.14
    POSITIVE LOGITS
     loved
    0.72
     relatives
    0.67
     family
    0.59
     Loved
    0.59
     relative
    0.57
     Relatives
    0.54
    relative
    0.49
     Relative
    0.47
    family
    0.47
    Relative
    0.43
    Act Density 0.326%

    No Known Activations