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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" along with personal pronouns indicating direction or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obi
    -0.16
    CRET
    -0.16
    Parcelable
    -0.15
    itch
    -0.15
    oÄŁ
    -0.14
    112
    -0.13
    isse
    -0.13
    iry
    -0.13
    arium
    -0.13
    yc
    -0.13
    POSITIVE LOGITS
    eventType
    0.16
    keh
    0.15
    ETA
    0.15
    unci
    0.15
    ignum
    0.14
     home
    0.14
    867
    0.14
    ATA
    0.14
    ucene
    0.14
     Hlav
    0.14
    Act Density 0.041%

    No Known Activations