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

    Neuronpedia

    INDEX
    Explanations

    terms related to trust and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erner
    -0.14
    blink
    -0.13
    orer
    -0.13
    rack
    -0.13
    711
    -0.13
    546
    -0.13
    inds
    -0.13
    ori
    -0.12
    resa
    -0.12
    thin
    -0.12
    POSITIVE LOGITS
     itself
    0.15
    -related
    0.14
    .nasa
    0.14
    -enabled
    0.14
    -containing
    0.14
    aaS
    0.14
     themselves
    0.14
    üzel
    0.13
    achuset
    0.13
    uÅŁ
    0.13
    Act Density 0.376%

    No Known Activations