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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating forms of communication or interaction with others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ester
    -0.16
     decre
    -0.14
    sons
    -0.14
    #End
    -0.13
    abil
    -0.13
    alam
    -0.13
    eya
    -0.13
    brook
    -0.12
    PROFILE
    -0.12
     chances
    -0.12
    POSITIVE LOGITS
     about
    0.21
     everyone
    0.21
    /about
    0.20
    _about
    0.20
     authorities
    0.19
    /email
    0.18
    åħ³äºİ
    0.18
     everybody
    0.18
    about
    0.17
     anyone
    0.17
    Act Density 0.251%

    No Known Activations