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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or speculation about future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TRACE
    -0.15
    plnÄĽ
    -0.14
     Poh
    -0.14
    ogui
    -0.14
    ASSES
    -0.14
    ctl
    -0.14
    ìĬ¤íģ¬
    -0.14
    .googlecode
    -0.13
    chter
    -0.13
    OKIE
    -0.13
    POSITIVE LOGITS
     whether
    0.30
     jury
    0.28
     Whether
    0.26
    whether
    0.24
    Whether
    0.24
     WHETHER
    0.23
    æĺ¯åIJ¦
    0.20
     Jury
    0.19
    ãģ©ãģĨ
    0.18
     Hopefully
    0.18
    Act Density 0.160%

    No Known Activations