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

    Neuronpedia

    INDEX
    Explanations

    references to hostility in various environments or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    hostile, hostility, animosity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.53
     Picchu
    -0.52
    Autoritní
    -0.51
     lass
    -0.50
    onActivityResult
    -0.49
     AppComponent
    -0.49
     apr
    -0.47
    Eras
    -0.47
     BnF
    -0.46
     Platon
    -0.46
    POSITIVE LOGITS
     hostile
    1.82
     hostility
    1.36
     unfriendly
    1.08
     hostilities
    0.94
     feind
    0.93
     antagonistic
    0.85
     Feind
    0.81
     enemy
    0.80
     aggressive
    0.79
    hos
    0.77
    Act Density 0.010%

    No Known Activations