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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a future time frame

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the passage of time or temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monstrous
    -0.64
     Bastard
    -0.62
     Stall
    -0.62
     Byte
    -0.62
     Sph
    -0.59
     Facilities
    -0.58
     Benefits
    -0.58
     Ammunition
    -0.58
     Parables
    -0.57
     BAS
    -0.57
    POSITIVE LOGITS
    adays
    1.14
    here
    0.93
    abouts
    0.80
    èª
    0.73
    lication
    0.71
    forth
    0.71
     defunct
    0.71
    ledged
    0.70
    endi
    0.70
    ivia
    0.69
    Act Density 0.022%

    No Known Activations