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

    Neuronpedia

    INDEX
    Explanations

    references to television hosts and their careers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iyan
    -0.15
    entai
    -0.15
    @student
    -0.15
    ckill
    -0.15
    ritten
    -0.14
    rana
    -0.14
    istent
    -0.14
    ÏĢη
    -0.13
    ladu
    -0.13
    allery
    -0.13
    POSITIVE LOGITS
     host
    0.68
     hosts
    0.65
     Host
    0.60
    Host
    0.54
    host
    0.52
    hosts
    0.52
     hosting
    0.51
    -host
    0.50
     HOST
    0.49
    HOST
    0.48
    Act Density 0.331%

    No Known Activations