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

    Neuronpedia

    INDEX
    Explanations

    verbs related to communication and interaction

    oai_token-act-pair · gpt-3.5-turbo

    instances of reported alarming events or crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     depends
    -0.62
    estern
    -0.56
     Currently
    -0.54
    quartered
    -0.54
    undrum
    -0.53
    ilial
    -0.53
     Allaah
    -0.52
    pires
    -0.50
    rentices
    -0.50
    icka
    -0.50
    POSITIVE LOGITS
     theirs
    0.62
    }.
    0.62
     scrut
    0.58
     panicked
    0.57
    their
    0.56
    ]).
    0.56
     afterward
    0.56
     culminating
    0.54
     enthusi
    0.54
     unison
    0.54
    Act Density 1.635%

    No Known Activations