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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hosting events or activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hosted" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    othing
    -0.68
     mistake
    -0.67
     brake
    -0.66
    lasses
    -0.66
     brakes
    -0.66
     bullets
    -0.66
     transgress
    -0.64
     tal
    -0.64
     confusion
    -0.61
     mentally
    -0.60
    POSITIVE LOGITS
     hosted
    3.61
     hosting
    2.20
     hosts
    1.98
    Host
    1.66
     host
    1.64
     sponsored
    1.63
    host
    1.59
     Host
    1.56
     chaired
    1.53
     convened
    1.46
    Act Density 0.011%

    No Known Activations