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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "actually" is used in the text

    oai_token-act-pair · gpt-3.5-turbo

    the word "actually" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VC
    -0.70
     Crus
    -0.67
    zy
    -0.65
     alas
    -0.65
    iously
    -0.65
     Division
    -0.62
    VK
    -0.62
     Camb
    -0.61
    Vert
    -0.61
     Directive
    -0.61
    POSITIVE LOGITS
     cared
    0.78
     bothered
    0.77
     existed
    0.76
     functioning
    0.74
     manage
    0.73
    incerity
    0.72
     harmed
    0.72
     bother
    0.70
     communicate
    0.69
     proposition
    0.68
    Act Density 0.067%

    No Known Activations